peer-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes academic manuscripts which are untrusted external inputs that could contain instructions designed to influence agent behavior. Ingestion points: Manuscripts accessed via Read and WebFetch tools. Boundary markers: None present to isolate manuscript content. Capability inventory: Bash, WebFetch, Read, Grep, and Glob. Sanitization: None provided for external content.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute bibliographical resolution scripts.
- [DYNAMIC_EXECUTION]: The skill executes scripts from a placeholder path () using the uv runner.
Audit Metadata