feature-prompt
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local repository files and incorporates it into output artifacts and project documentation.
- Ingestion points: The skill reads from GLOSSARY.md, CONTEXT.md, GLOSSARY-MAP.md, and various ADR files to gather domain terminology and project context.
- Boundary markers: While the skill uses a strict output contract and fixed headers, it lacks explicit delimiters or instructions to the model to ignore potential malicious instructions embedded within the processed repository files.
- Capability inventory: The skill possesses file-read and file-write capabilities, specifically creating new files in specs/prompts/ and updating GLOSSARY.md.
- Sanitization: There is no evidence of specific sanitization or filtering applied to the content retrieved from the repository files before it is processed or written back to the filesystem.
Audit Metadata