notion
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources.
- Ingestion points: The tools
notion-search,notion-fetch, andnotion-get-commentsinapp.pyretrieve content from Notion workspaces, which can include data from connected third-party services like Slack, GitHub, and Jira. - Boundary markers: The skill does not implement boundary markers or specific instructions to the agent to disregard embedded commands in the fetched content.
- Capability inventory: The skill provides significant write capabilities, including
notion-create-pages,notion-update-page,notion-move-pages, andnotion-create-databaseinapp.py, which could be abused if an agent obeys instructions hidden in fetched data. - Sanitization: No sanitization or validation of the fetched Notion content is performed before it is returned to the agent context.
Audit Metadata