implement
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted documents (specs or tickets) to guide development tasks, creating an injection surface.\n
- Ingestion points: The agent reads user-provided "specs or tickets" as referenced in
SKILL.md.\n - Boundary markers: No specific delimiters or safety instructions are defined to separate user data from system instructions within these inputs.\n
- Capability inventory: The skill authorizes the agent to write code to the local file system, execute commands for typechecking and testing, and perform git commits.\n
- Sanitization: The instructions do not specify any validation or filtering of the content retrieved from the specs or tickets.
Audit Metadata