verify

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites to verify factual claims, which presents a surface for indirect prompt injection.
  • Ingestion points: External content retrieved via the WebSearch and WebFetch tools (SKILL.md).
  • Boundary markers: Absent. The instructions do not include specific delimiters or warnings to ignore instructions that might be embedded in the retrieved web content.
  • Capability inventory: The skill uses the Edit tool to modify local project files (specifically notes) based on the information it finds (SKILL.md).
  • Sanitization: Absent. The skill does not explicitly describe sanitization or filtering of the content retrieved from the web before processing it.
  • [EXTERNAL_DOWNLOADS]: The skill fetches information from external websites using WebFetch and WebSearch to verify claims.
  • Evidence: It prioritizes well-known and authoritative sources such as Wikipedia, Google Scholar, JSTOR, and official publisher websites (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 03:18 AM
Security Audit — agent-trust-hub — verify