find
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and summarizes titles and metadata from Notion, which are untrusted external inputs.\n
- Ingestion points: Search results containing titles, types, and parent locations of Notion pages and databases (SKILL.md).\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat search results as data rather than instructions.\n
- Capability inventory: The skill invokes the Notion MCP server to perform searches and format results.\n
- Sanitization: The skill does not perform any validation or sanitization of the retrieved titles before providing them to the agent.
Audit Metadata