feature-tracking
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from REQUIREMENTS.md and TODO.md which could potentially contain malicious instructions targeting the agent. Ingestion points: REQUIREMENTS.md, TODO.md. Boundary markers: None specified in the instructions for separating data from potential instructions. Capability inventory: Read, Write, Edit, Grep, Glob, Bash, TodoWrite. Sanitization: No explicit sanitization or validation of the text content from requirements files is documented before processing.
Audit Metadata