content-governance

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external sources (Google Docs and Notion pages) and performs write operations to the same platforms, creating an attack surface where malicious content could influence agent behavior.
  • Ingestion points: Content is retrieved via mcp__google-workspace__get_doc_content and mcp__claude_ai_Notion__notion-fetch as part of the synchronization process.
  • Boundary markers: The instructions do not define delimiters or explicit "ignore embedded instructions" warnings for the ingested body content before it is processed.
  • Capability inventory: The skill has permission to create and update files in Google Drive and pages in Notion via MCP tools.
  • Sanitization: No explicit sanitization of the input text is mentioned to mitigate potential embedded instructions within the newsletters.
  • [EXTERNAL_DOWNLOADS]: The documentation references an external repository for the installation of the skill.
  • Pattern: The command npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill content-governance is provided for setup.
  • Context: The source is the author's own repository, representing a standard installation pattern for this ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 04:41 PM
Security Audit — agent-trust-hub — content-governance