analyze-paper
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (academic papers) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill accepts a
<paper-path>argument and uses file tools to read and extract text from these external documents (SKILL.md, Step 1). - Boundary markers: The instructions do not define explicit delimiters or include warnings to the agent to ignore or disregard instructions embedded within the papers themselves.
- Capability inventory: The skill possesses file reading (PDF/text extraction) and file writing capabilities (Step 3: Write Output) which could be misused if the agent obeys instructions found in the analyzed data.
- Sanitization: There is no mention of sanitization, filtering, or validation of the extracted content before the agent processes it and writes findings to the output file.
Audit Metadata