Fact Check

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected in the skill instructions or methodology.- [EXTERNAL_DOWNLOADS]: The skill describes patterns for fetching content from well-known technical documentation sources and official standards organizations, including MDN Web Docs, W3C, WHATWG, and OWASP, for the purpose of claim verification.- [PROMPT_INJECTION]: No direct prompt injection or safety bypass instructions were found. The skill does have an indirect prompt injection surface due to its data-ingestion nature:
  • Ingestion points: External content is ingested via WebFetch, WebSearch, and get-library-docs tools from SKILL.md.
  • Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions within ingested data.
  • Capability inventory: The skill uses read-only tools for search and documentation retrieval; no code execution or file-write capabilities were identified.
  • Sanitization: No explicit sanitization or filtering of external content is specified in the methodology.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:34 AM
Security Audit — agent-trust-hub — Fact Check