scribe-role-skill
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the project codebase (source code, manifests, and existing documentation) to generate new documentation content.
- Ingestion points: Step 1.1 (Codebase Analysis) reads files using tools like tree, find, and cat.
- Boundary markers: None; the skill processes project files directly without isolation delimiters or "ignore" instructions for embedded content.
- Capability inventory: The skill possesses file-read (cat, tree, find) and file-write capabilities across the documentation directory.
- Sanitization: No specific filtering, escaping, or validation of the content read from the external codebase is defined.
Audit Metadata