tasks-plan
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data fetched from external Notion pages, which could contain malicious instructions designed to influence the agent's behavior.\n- Ingestion points: Step 1 in SKILL.md fetches specification content, linked pages, and references using Notion MCP tools.\n- Boundary markers: Instructions lack delimiters or warnings to ignore instructions embedded within the source content.\n- Capability inventory: The skill has permissions to write new pages and create tasks in the Notion workspace via MCP tools.\n- Sanitization: No validation or sanitization of fetched data is mentioned before it is analyzed and used for plan generation.
Audit Metadata