Fact Check

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional content and methodology for verification tasks. No malicious code, obfuscation, or unauthorized access attempts were detected.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and repositories from trusted organizations such as Microsoft, Meta, and Vercel. These references are for documentation purposes and do not involve the execution of untrusted external scripts.
  • [PROMPT_INJECTION]: The skill processes external data to verify claims, which is a potential surface for indirect prompt injection.
  • Ingestion points: Data retrieved from external URLs and search results via WebFetch and WebSearch tools.
  • Boundary markers: None explicitly defined for external content.
  • Capability inventory: The skill uses tools for searching and documentation fetching; it does not request generic shell access or file system modification capabilities.
  • Sanitization: No specific sanitization or filtering of fetched content is described. The skill's requirement for confidence assessment and discrepancy reporting acts as a procedural safeguard against malicious data influencing the agent's conclusions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 05:21 AM
Security Audit — agent-trust-hub — Fact Check