skills/clerk/skills/clerk-testing/Gen Agent Trust Hub

clerk-testing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and setup guides from official Clerk domains (clerk.com) and references the vendor's official GitHub repository for demo code.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses WebFetch to ingest external content from documentation pages, creating a potential surface for indirect instructions if the remote documentation pages were to contain adversarial content.
  • Ingestion points: SKILL.md (Decision Tree and Workflow sections) references external URLs intended for WebFetch.
  • Boundary markers: Absent; the skill does not specify delimiters for the fetched content.
  • Capability inventory: The skill leverages the WebFetch tool to retrieve information from the web.
  • Sanitization: Not explicitly defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:39 AM