breakdown-feature-implementation
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest a Feature PRD and generate an implementation plan which it then instructs the agent to save to the local file system, creating a vulnerability surface where malicious instructions in a PRD could be executed.
- Ingestion points: The Feature PRD is ingested through the context template at the end of SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the untrusted PRD content.
- Capability inventory: The skill directs the agent to save files to the
/docs/ways-of-work/plan/directory, involving file system write capabilities. - Sanitization: No input validation, escaping, or sanitization logic is provided to ensure the PRD content does not contain prompt injection attacks.
Audit Metadata