NYC

notion-spec-to-implementation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill exhibits a surface for indirect prompt injection because it fetches and parses external specification documents from Notion. This is a primary function of the skill and no malicious exploitation patterns were observed.
  • Ingestion points: The Notion:notion-fetch tool is used in SKILL.md and reference/spec-parsing.md to retrieve the full content of Notion pages.
  • Boundary markers: Absent. The skill does not explicitly provide delimiters or 'ignore' instructions for the fetched content.
  • Capability inventory: The skill has the ability to create and update Notion pages via Notion:notion-create-pages and Notion:notion-update-page (SKILL.md).
  • Sanitization: Absent. Content is parsed for structured requirements using natural language processing patterns defined in reference/spec-parsing.md.
  • Data Exposure & Exfiltration (SAFE): No evidence of hardcoded credentials or network calls to external, non-whitelisted domains was found. Operations are confined to the Notion workspace.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not install third-party packages or execute remote scripts. It relies solely on built-in Notion integration tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:52 PM