internal-documentation
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the repository to generate or update documentation, creating a surface for indirect prompt injection.
- Ingestion points:
SKILL.mdinstructs the agent to "Inspect the relevant code, configuration, tests, and existing docs before describing behavior." - Boundary markers: The instructions do not specify any delimiters or warnings to ignore potentially malicious instructions embedded within the code or comments being documented.
- Capability inventory: The skill's primary purpose involves reading files and writing/updating documentation files based on those inputs.
- Sanitization: There is no mention of sanitizing or validating the content extracted from the source files before it is processed by the agent.
- [NO_CODE]: The skill consists entirely of instructional markdown and configuration files without any embedded scripts or executable code, which limits the direct execution risk.
Audit Metadata