Changelog Generator
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data which creates a surface for indirect prompt injection. 1. Ingestion points: Git commits and feature lists provided by the user. 2. Boundary markers: Absent. No delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: File creation capabilities via create_docx and md_to_docx tools. 4. Sanitization: No sanitization of user-provided content is performed.
Audit Metadata