Skills
skills/openai/skills/notion-spec-to-implementation/Gen Agent Trust Hub

notion-spec-to-implementation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection as it processes external Notion specifications to generate tasks and plans.\n
  • Ingestion points: Specification content is fetched from Notion via Notion:notion-fetch as documented in SKILL.md and reference/spec-parsing.md.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the implementation plan templates.\n
  • Capability inventory: The skill has the ability to write to the user's workspace using Notion:notion-create-pages and Notion:notion-update-page.\n
  • Sanitization: No sanitization or validation of the fetched Notion page content is specified before processing.\n- [External Downloads] (LOW): The agent configuration in agents/openai.yaml references an external MCP server at https://mcp.notion.com/mcp. Although this is the official endpoint for the service and core to the skill's function, it is not part of the predefined trusted source list.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:55 PM