docs-tooling-notion
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Data Ingestion and Processing]: The skill is designed to monitor and document changes to repository files such as scripts and workflows. This introduces a potential surface for indirect prompt injection if the files being documented contain instructions intended to influence the agent's behavior.
- Ingestion points: The agent reads local files (e.g., contents of
scripts/and.github/workflows/) to generate documentation. - Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the files being documented.
- Capability inventory: The skill utilizes Notion-specific tools (
notion-fetch,notion-update-page) to modify external documentation. - Sanitization: No explicit sanitization or filtering of the file contents is specified before they are processed and sent to Notion.
- [Use of External Service Identifiers]: The skill hardcodes several Notion page and database IDs to ensure documentation is routed correctly. These identifiers are specific to the intended workspace and are necessary for the skill's automation logic.
- [Dependency on External Tools]: Functionality depends on the availability of the Notion MCP server tools. Users should ensure these tools are from a trusted source and configured with appropriate permissions for the target Notion workspace.
Audit Metadata