paper-self-review
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and process untrusted external data (academic papers in .tex, .pdf, or .qmd formats).
- Ingestion points: The skill instructions in 'Step 1: Locate and Read the Paper' direct the agent to read the full content of user-provided files.
- Boundary markers: The instructions do not include boundary markers or specific warnings to the agent to ignore any instructions or overrides that might be contained within the paper text itself.
- Capability inventory: The skill's primary capability is text analysis and the generation of a markdown report. It does not appear to invoke dangerous tools such as shell execution or network operations.
- Sanitization: There is no evidence of sanitization or filtering of the content read from the external files before it is processed by the agent.
Audit Metadata