planner
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting untrusted data from multiple sources.
- Ingestion points: The skill accepts arbitrary planning requests from the user and fetches external documentation using the 'Context7' skill (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or "ignore instructions" directives when processing content retrieved from external documentation.
- Capability inventory: The skill is capable of performing network read operations (via Context7) and writing markdown files to the local file system (SKILL.md, Phase 3: Save).
- Sanitization: There is no evidence of sanitization or validation for the content retrieved from external APIs or libraries before it is incorporated into the final plan file.
Audit Metadata