how
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize information from repository files and specific rule documents to explain system flows. This creates a surface where instructions hidden within the analyzed source code could potentially influence the agent's behavior.
- Ingestion points: Processes repository source files and local rule documents such as
main-context.md,code-quality.md, andcode-structure.md. - Boundary markers: The instructions do not specify the use of delimiters or warnings to separate external data from system instructions.
- Capability inventory: The skill is strictly limited to read-only file access; it explicitly forbids editing code, opening tickets, or initiating build tasks.
- Sanitization: There are no requirements for filtering, escaping, or validating the content retrieved from repository files.
Audit Metadata