blog-factcheck

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is to verify statistical claims by reading user-specified files and fetching external URLs. These actions are aligned with the stated purpose and use standard tools like WebFetch.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from blog posts and external websites. * Ingestion points: Target blog post files and source content retrieved via WebFetch. * Boundary markers: The instructions do not define delimiters or isolation warnings for processed text. * Capability inventory: The skill uses file reading and network access (WebFetch). * Sanitization: External content is processed directly without explicit sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:44 AM
Security Audit — agent-trust-hub — blog-factcheck