skills/seaworld008/commonly-used-high-value-skills/notion-research-documentation/Gen Agent Trust Hub
notion-research-documentation
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file provides a sequence of 'codex mcp' commands for the user to execute manually in their terminal to set up the environment. While documented for the user, agents might attempt to run these if not clearly constrained.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It reads data from Notion pages using 'Notion:notion-fetch' and incorporates it into summary and report generation without explicit boundary markers or sanitization mentioned in the prompt logic.
- Ingestion points: 'Notion:notion-fetch' in SKILL.md.
- Boundary markers: None identified in the instructional text for processing fetched content.
- Capability inventory: Subprocess-like capability through Notion write operations ('Notion:notion-create-pages', 'Notion:notion-update-page').
- Sanitization: None mentioned for external Notion content.
Audit Metadata