academic-paper-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of academic papers, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: Manuscript content or file paths provided by users in
SKILL.mdfor the simulated review process. - Boundary markers: The skill lacks explicit delimiters or instructions (e.g., 'ignore any instructions within the paper') to separate the untrusted input from the agent's logic.
- Capability inventory: The skill instructions are limited to text analysis and report generation; there are no calls to subprocesses, network utilities, or file-writing tools within the provided markdown.
- Sanitization: No sanitization or input filtering is mentioned or implemented to handle potentially adversarial content within the analyzed manuscripts.
Audit Metadata