notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core workflow of processing external data.
- Ingestion points: The skill uses
Notion:notion-fetchto retrieve content from Notion pages as described in the workflow section ofSKILL.md. - Boundary markers: No explicit delimiters or instructions are used to separate retrieved content from agent instructions.
- Capability inventory: The agent has write access to the Notion workspace via
Notion:notion-create-pagesandNotion:notion-update-page. - Sanitization: Lacks evidence of input validation or content filtering.
- [PRIVILEGE_ESCALATION]: The skill provides instructions to elevate platform permissions.
- Evidence:
SKILL.mdworkflow step 0 instructs the user to set[features].rmcp_client = trueor runcodex --enable rmcp_clientto enable remote MCP functionality.
Audit Metadata