paper-analyst
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as intended for academic research and displays no malicious intent or suspicious commands.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external content from academic papers. 1. Ingestion points: External content fetched via Exa search, WebFetch, and Semantic Scholar (SKILL.md). 2. Boundary markers: Not explicitly defined for the processing of third-party paper content. 3. Capability inventory: The agent writes output to 'paper_analyses/' and 'comparison_tables.md' (SKILL.md). 4. Sanitization: No specific validation or filtering of paper content is mentioned. This surface is expected for a research-oriented tool and does not indicate a security failure.
Audit Metadata