crypto-compare

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external websites, social media platforms, and community forums, creating a surface for indirect prompt injection if those sources contain malicious instructions.
  • Ingestion points: Content retrieved via WebSearch and WebFetch from sources including social media, GitHub, and crypto data providers listed in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the fetched data.
  • Capability inventory: The agent is authorized to perform network searches, fetch remote content, and write output to a markdown file.
  • Sanitization: The skill lacks requirements for sanitizing or validating external content before it is processed by the model or written to the output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:34 AM
Security Audit — agent-trust-hub — crypto-compare