notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external Notion pages without explicit sanitization or boundary markers.
- Ingestion points: The skill uses
Notion:notion-search,Notion:notion-fetch, andNotion:notion-query-data-sourcesinSKILL.mdto retrieve arbitrary content from a Notion workspace. - Boundary markers: The instructions lack specific delimiters (like XML tags or triple quotes) to separate untrusted content from the agent's core instructions, increasing the risk that instructions embedded in a Notion page could be obeyed.
- Capability inventory: The skill possesses the capability to write back to the workspace using
Notion:notion-create-pagesandNotion:notion-create-comment, which could be exploited to spread malicious content or modify data. - Sanitization: There are no documented mechanisms for input validation or filtering of the fetched content to prevent the execution of embedded prompts.
Audit Metadata