notion-pm
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from Notion databases and third-party integrations (Jira, Linear, GitHub), which introduces an inherent surface for indirect prompt injection where malicious instructions could be embedded in external content.
- Ingestion points: Data retrieved from Notion API queries, database properties, and external tool syncs as described in
references/notion-api-patterns.mdandreferences/notion-pm-playbook.md. - Boundary markers: No explicit instruction for the use of delimiters or boundary markers is provided to protect against untrusted content in processed strings.
- Capability inventory: The skill enables the agent to perform write operations across the workspace, including creating/updating pages and properties and appending block children.
- Sanitization: No specific sanitization or validation logic is defined for external data before it is interpolated into the Notion workspace.
Audit Metadata