literature-research
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface where malicious instructions embedded in external research sources could influence the agent's behavior.
- Ingestion points: The skill explicitly instructs the agent to "Investigate state-of-the-art articles on the internet," which brings untrusted data into the execution context.
- Boundary markers: Absent. The instructions do not provide delimiters or "ignore instructions" markers to help the agent distinguish between research data and operational commands.
- Capability inventory: The skill allows the agent to write files directly to the repository ("Write the findings to a single Markdown file"), which could be exploited if malicious content is processed.
- Sanitization: Absent. There is no mention of validating, escaping, or filtering the external content before it is committed to the file system.
Audit Metadata