markdown-plan
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input and writes it directly to a markdown file on the local filesystem.\n- Ingestion points: User requests (SKILL.md).\n- Boundary markers: None defined for the content of the plan file.\n- Capability inventory: Local file writing restricted to the
~/.cursor/plans/directory (SKILL.md).\n- Sanitization: No explicit sanitization or validation of user-supplied content is performed before writing.
Audit Metadata