docs-architect
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to perform deep analysis of external codebases, creating an attack surface where instructions embedded in code comments or strings within the repository could potentially influence behavior.
- Ingestion points: Discovery phase involving analysis of codebase structure, dependencies, and data flows (SKILL.md).
- Boundary markers: Absent; instructions lack explicit directives to treat analyzed code strictly as data or to use delimiters to separate instructions.
- Capability inventory: Focused on Markdown generation; however, the skill lacks specific tool restrictions in its configuration, allowing potential file-system access.
- Sanitization: Absent; the skill does not specify methods for filtering or sanitizing content before processing.
Audit Metadata