planner
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting and processing untrusted data to generate plans.\n
- Ingestion points: The skill research phase (Phase 0) involves reading the local codebase, and Phase 2 explicitly fetches external documentation from APIs, libraries, or services via the 'Context7' skill.\n
- Boundary markers: There are no defined delimiters or 'ignore' instructions provided to the agent to distinguish between the skill's operational instructions and data retrieved from external sources.\n
- Capability inventory: The skill is designed to perform codebase research (read access) and save plan files to the local filesystem (write access).\n
- Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from the codebase or external documentation before it is used to draft the implementation plan.
Audit Metadata