plan-feature
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface because it instructs the agent to read and research existing repository code to inform the feature plan. This could allow malicious instructions embedded in the codebase (e.g., in comments) to influence the agent's planning logic or the verification commands suggested in the plan file.
- Ingestion points: Reads existing files in the repository, patterns, and libraries.
- Boundary markers: No specific boundary markers or instructions to disregard embedded commands in source code are provided.
- Capability inventory: The skill writes a plan file to the local filesystem (typically in a 'plans/' directory) and suggests shell commands for verification steps.
- Sanitization: No sanitization is performed on the content read from the repository code.
Audit Metadata