tasks-setup
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Notion board URLs to inspect their structure.
- Ingestion points: Board URLs provided by the user (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Uses Notion MCP tools to read database schema and property definitions.
- Sanitization: The skill relies on the agent's underlying tool implementation for data handling.
Audit Metadata