proof-writer
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local files and user arguments to extract mathematical claims, making it susceptible to indirect prompt injection. 1. Ingestion points: Theorem statements, local notes, appendix drafts, and existing proof files (Workflow Step 1). 2. Boundary markers: None defined to separate external content from instructions. 3. Capability inventory: The skill uses Read, Write, Edit, Grep, and Glob tools for file manipulation. 4. Sanitization: No sanitization or validation of the ingested file content is performed before processing.
Audit Metadata