#FactCheck - Old Bareilly Lathi-Charge Video Falsely Linked to Lucknow Protest

Introduction

‍

In today’s digital environment, national security challenges extend well beyond traditional military domains. One growing concern is the unauthorised extraction of information, which is increasingly being used through subtle and gradual methods rather than overt force. Recent advisories point to a rising pattern in which foreign organisations seek to recruit individuals to collect and handle sensitive material, often using financial cybercrime networks as part of their operational ecosystem. This trend has implications for journalists, defence personnel, researchers, students, and academics working in strategic, geopolitical, and security-related fields. The core risk lies in the fact that these activities can proceed quietly and without coercion, with participants sometimes unaware that their actions may contribute to intelligence gathering efforts.

‍

Digital Platforms as Vectors for Targeted Recruitment

‍

Professional networking and job portals have become central to modern career development. The same visibility that supports professional advancement is being misused by others. Foreign entities reportedly use these platforms to identify individuals with experience in journalism, defence services, strategic studies, cybersecurity, and international relations.

Early-career professionals and students from reputed Higher Education Institutions (HEIs) are particularly vulnerable because they seek freelance work, research experience and international partnerships. Initial outreach is often framed as legitimate consultancy, research assistance, or content development work, which creates the impression of professional credibility through normal business operations.

‍

Task-Based Information Extraction

‍

The organisation assigns writing and research duties to new employees, which seem simple to perform. The topics of source-based articles and analytical pieces include the following two subjects about India.

• The first subject examines India's foreign relations with its strategic partnerships.
• The second subject investigates how armed forces operate through different military movements.
• The third subject focuses on defence procurement activities, which include weapon system development and modernisation projects.
• The fourth subject investigates military activities through joint training exercises and war simulation exercises.

The public possesses most of this knowledge, but its threat emerges from the process of collecting and interpreting data with contextual information. The collection of insights from various sources enables organisations to identify operational patterns, strategic priorities and capacity evaluations which go beyond particular data points.

‍

The Financial Cybercrime Nexus

‍

The financial system that pays contributors presents itself as a major problem for this activity. Payments are often routed through:

• Indian bank accounts, including student accounts
• Funds originating from cyber fraud or financial crimes
• Occasional overseas transfers structured to avoid scrutiny

The system establishes a direct connection between financial cybercrime activities and the theft of confidential information, which brings unintentional danger of legal issues and public image damage to those involved. The Indian legal system considers all connections to illegal financial activities as serious offenses even when the person involved did not intend to commit any crime.

‍

Concealed Identities and Data Harvesting
‍

The entities that conduct recruitment activities willfully hide their real identities. The organisation uses intermediaries for their operations, which they present as foreign consulting firms, think tanks and analytics companies. Contributors who have defence or security experience will face requests to provide their personal data, which includes their PAN and Aadhaar information.

The collection of such data raises significant concerns. The system creates permanent privacy hazards that permit unauthorised access to personal data and identity theft and coercive practices. The ultimate use of this information often remains opaque to the individuals providing it.
‍

Why Incremental Leakage Matters
‍

The threat operates silently because it lacks the visibility of major cyberattacks. The combined effect of all articles and research notes becomes dangerous because no single element can cause harm. Hostile organisations can use incremental information leakage to undermine national security because they can analyse their gathered data to create:

• maps of strategic capabilities,
• defence readiness evaluations,
• security and foreign policy narrative control.

The process of information sovereignty erosion occurs through the establishment of undefined boundaries between journalism and academic research, and consultancy and strategic analysis. The lack of clear boundaries between journalism and academic research, consultancy and strategic analysis makes it difficult to determine who is responsible for research outcomes.
‍

The Role of Institutions and Individuals
‍

The universities and media outlets, together with the professional organizations have essential functions in their quest to diminish environmental effects. The organisation should perform the following proactive steps:

• The organisation should organise training programs which will educate people about its services.
• The organisation should require researchers to conduct thorough investigations before they accept paid assignments for research work and writing tasks.
• The organisation should recommend that people do not share their identity documents except when their institution requires it for authentication purposes.
• The organisation should create specific methods to report any suspicious activities that people might encounter.

Students and professionals need to understand that their specialised knowledge and trustworthiness can be used against them. People must protect their digital identities through three actions, which include verifying their affiliations and assessing the complete effects of their daily activities.
‍

Conclusion

‍

Cyber enabled threats to national security increasingly operate in grey zones, which makes their legality, legitimacy, and true intent difficult to assess. The convergence of foreign recruitment efforts, financial cybercrime, and covert information gathering creates a persistent risk that is still not widely recognised or fully understood. The state does not bear exclusive responsibility for protecting sensitive information. National resilience in an interconnected knowledge economy requires organisations to develop three core capacities, which include institutional awareness and restraint and institutional vigilance. Cyber resilience depends on two essential factors, which include secure systems and informed citizens, because data continues to determine power relationships.
‍

References
‍

• https://reports.weforum.org/docs/WEF_Global_Cybersecurity_Outlook_2025.pdf
• https://www.cyber-espionage.ch/
• https://www.theguardian.com/world/2025/nov/18/mi5-issues-alert-to-mps-and-peers-over-chinese-espionage
• http://cybercrimejournal.com/menuscript/index.php/cybercrimejournal/article/download/263/92
• https://www.researchgate.net/publication/368461675_Cyber_Espionage_Consequences_as_a_Growing_Threat

‍

Introduction
‍

Agentic AI systems are autonomous systems that can plan, make decisions, and take actions by interacting with external tools and environments. But they shift the nature of risk by blurring the lines among input, decision, and execution. A conventional model generates an output and stops. An agent takes input, makes plans, invokes tools, updates its state and repeats the cycle. This creates a system where decisions are continuously revised through interaction with external tools and environments, rather than being fixed at the point of input.

This means the attack surface expands in size and becomes more dynamic. Instead of remaining confined to components as in traditional computational systems, they spread in layers and can continue to grow through time. To understand this shift, the system can be analysed through functional layers such as inputs, memory, reasoning, and execution, while recognising that risk does not remain isolated within these layers but emerges through their interaction.

‍

‍

Agentic AI Attack Surface

‍

A layered view of how risks emerge across input, memory, reasoning, execution, and system integration, including feedback loops and cross-system dependencies that amplify vulnerabilities.
‍

Input Layer: Where Untrusted Data Becomes Control
‍

The entry point of an agent is no longer one prompt. The documents, APIs, files, system logs and the outputs of other agents can now be considered input. This diversity is significant due to the fact that every source of input carries its own trust assumptions, and in the majority of cases, they are weak.

The most obvious threat is prompt injection, where inputs are treated as instructions rather than data. Since inputs are treated as instructions, a virus, a malicious webpage, or a document can contain instructions that override system goals without necessarily being detected as something harmful.

Indirect prompt injection extends this risk beyond direct user interaction. Instead of targeting the interface, attackers compromise the retrieval process by embedding malicious instructions within external data sources. When the agent retrieves and processes the data, it treats the embedded content as legitimate input. As a result, the attack is executed through normal reasoning processes, allowing the system to act on untrusted data without recognising the manipulation.

Data poisoning also occurs at runtime. In contrast to classical poisoning (where training data is manipulated), runtime poisoning distorts the agent’s perception of its environment as it runs. This can change decisions without causing apparent failures.

Obfuscation introduces another indirect attacker vector. Encoded instructions or complicated forms may bypass human review but remain readable to the model. This creates asymmetry whereby the system knows more about the attack than those operating it. Once compromised at this layer, the agent implements compromised instructions which affect downstream operations.
‍

Context and Memory: Persistence of Influence
‍

Agentic systems depend on memory to operate efficiently. They often retain context across sessions and frequently store information between sessions.

This introduces a different type of risk: persistence. Through memory poisoning, attackers can insert false or adversarial information into sorted context, which then influences future decisions. Unlike prompt injection, which is often limited to a single interaction, this effect carries forward. Over time, the agent begins to operate on a distorted internal state, shaping decisions in ways that may not be immediately visible.

Another issue is cross-session leakage. Information in a particular context may be replayed in a different context when memory is being shared or there is insufficient memory separation. This is specifically dangerous in those systems that combine retrieval and long-term storage. The context management in itself becomes a weakness. Agents are required to make decisions on what to retain and what to discard. This is susceptible to attackers who can flood the context or manipulate what is still visible and indirectly affect reasoning.

The underlying problem is structural. Memory turns data into a state. Once state is corrupted, the system cannot easily distinguish valid knowledge from adversarial influence.

The issue is structural. Memory converts temporary data into a persistent state. Once this state is weakened, the system cannot reliably separate valid information from adversarial influence, making recovery significantly more difficult.
‍

Reasoning and Planning: Manipulating Intent Without Breaking Logic
‍

The reasoning layer is where agentic AI stands apart from traditional systems. The model no longer reacts to inputs alone. It actively breaks down objectives, analyses alternatives, and ranks actions.

At the reasoning stage, the nature of risk shifts. The concern is no longer limited to injecting instructions, but to influencing how decisions are made. One example is goal manipulation, where the agent subtly reinterprets its objective and produces outcomes that are technically correct but strategically harmful. Reasoning hijacking operates within intermediate steps, altering how constraints are evaluated or how trade-offs are prioritised. The system may remain internally consistent, which makes such deviations difficult to detect.

Tool selection becomes a critical control point. Agents decide which tools to use and when, so influencing these choices can redirect execution without directly accessing the tools themselves. Hallucinations also take on a different role here. In static systems, they remain errors. In agentic systems, they can trigger actions. A perceived need or incorrect judgement can translate into real-world consequences.

This layer introduces probabilistic failure. The system is not fully weakened, but it is nudged towards decisions that appear reasonable yet are incorrect. The risk lies in how those decisions are justified.

‍
‍Tool and Execution: When Decisions Gain Reach
‍

Once an agent begins interacting with tools, its behaviour extends beyond the model into external systems. APIs, databases, and services become part of the execution path.

One key risk is the use of unauthorised tools. When agents operate with broad permissions, any manipulation of the upstream can be converted into real-world actions. This makes access control a central security concern. Command injection also takes a different form here. The agent generates commands based on its reasoning, so if that reasoning is compromised, the resulting actions may still appear valid despite being harmful.

External tool outputs introduce another risk. If these systems return corrupted or misleading data, the agent may accept it without verification and incorporate it into its decisions. It is also becoming increasingly reliant on third-part tools and plugins adds to this exposure. If these components are compromised, they can affect behaviour without directly attacking the core system, creating a supply-side risk.

At this stage, the agent effectively operates as an insider. It holds legitimate credentials and interacts with systems in expected ways, making misuse harder to identify.
‍

Application and Integration: System-Level Exposure
‍

Agentic systems rarely operate in isolation. They are embedded in larger environments, interacting with identity systems, business logic, and operational workflows.

Access control becomes a major vulnerability. Agents tend to operate across multiple systems with various permission models, creating irregularities that can be exploited. Risks also arise from identity and delegation. In case an agent is operating on behalf of a user, then any vulnerabilities in authentication or session management can allow attackers to assume that authority.

Workflow execution amplifies these risks. Agents can initiate multi-step processes such as transactions, updates, or approvals. Manipulating a single step can change the result of the entire workflow. As integrations increase, so do the number of interaction points, making cumulative risk harder to track.

At this layer, failures are not isolated. They propagate into business operations, making consequences harder to contain.
‍

Output and Action: Where Failures Become Visible
‍

The output layer is where failures become visible, though they rarely originate there.

Data leakage has been a key concern. Agents may disclose information they are allowed to access, especially when tasks boundaries are not clearly defined. Misinformation and unsafe outputs are also important, particularly when outputs directly influence actions or decisions.

Generated code and commands introduce execution risk. If outputs are used without validation, errors or manipulations can have system-level effects. The shift towards autonomous action increases this risk, as small upstream deviations can lead to significant consequences without human intervention. This layer reflects symptoms rather than root causes. Addressing it alone does not reduce the underlying risk.
‍

Beyond Layers: The Missing Dimension
‍

A layered view helps, but it does not capture the full picture. Agentic systems are defined by continuous interaction across layers.

The key missing dimension is the runtime loop. Inputs shape reasoning, reasoning drives action, and actions feed back into both reasoning and memory. These cycles create feedback loops, where small manipulations may escalate over time. This also reduces observability. With multiple interacting components, it becomes difficult to trace cause and effect or identify where failures originate.

Supply chain dependencies add another layer of risk. Models, datasets, APIs, and plugins each introduce their own points of failure. A compromise at any of these points can propagate across the system. The attack surface also includes governance. Weak supervision, unclear responsibility, or excessive autonomy increase overall risk. Human control is not external to the system; it is part of its security.
‍

Conclusion: Structuring the Attack Surface
‍

Agentic AI expands the attack surface beyond traditional systems. It is both recursive and stateful. Risk does not just accumulate across layers; it moves and changes as the system operates.

Any useful representation must go beyond a linear stack. It should capture feedback loops, persistent state, and cross-layer dependencies that characterise the way these systems actually behave. The system is not a pipeline but a cycle. That is where both its capability and its risk emerge.

‍

Executive Summary

‍

An image of a banknote featuring Iran’s Supreme Leader Ayatollah Khamenei is going viral on social media, with claims that Iran’s central bank has issued a newly designed 5 million rial note bearing his portrait. However, a fact-check by the CyberPeace Research Wing  has found the claim to be misleading.

‍

Claim
‍

The image was shared by a verified user, “Sprinter Press Agency,” on X (formerly Twitter), claiming that the Central Bank had introduced a new banknote design featuring the leader of the Islamic Revolution.

• https://x.com/ImHuMeer786H/status/2048042719231291661

‍

‍

Fact Check

‍

To verify the claim, relevant keywords were searched across multiple credible sources. No reports were found from any reputable international media outlet, Iranian government platform, or the Central Bank of Iran confirming the release of such a banknote. A technical analysis of the viral image was also conducted. According to the AI detection tool Zhuque AI Detection Assistant, there is a 63.8% probability that the image is AI-generated, raising further doubts about its authenticity.

‍

‍

Conclusion:
‍

The claim that Iran’s central bank has issued a new 5 million rial banknote featuring Ayatollah Khamenei is misleading. There is no official confirmation of such a release, and available evidence suggests that the viral image is either edited or AI-generated.

‍