proposal-review
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a content reviewer for thesis proposals. It is restricted to reading local guidelines and the user's proposal, and writing a markdown review file. No network operations, credential access, or execution of external code were detected.- [PROMPT_INJECTION]: The skill processes untrusted external content (thesis proposals and workspace configuration files), creating an attack surface for indirect prompt injection. However, the impact is minimal as the agent only performs text analysis and generates a review file.
- Ingestion points: Thesis proposal content and
workspace guidelines.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate input data from instructions.
- Capability inventory: File reading, Markdown file writing (
<slug>-review.md), and chat output. - Sanitization: No input validation or sanitization is performed on the ingested content.
Audit Metadata