reputation-reviews

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted review data from external websites, creating a surface for indirect prompt injection.\n
  • Ingestion points: Data is collected from various review platforms such as Google, Yelp, and Trustpilot using web search and fetch tools.\n
  • Boundary markers: The instructions lack specific delimiters or warnings to treat fetched review text as data rather than instructions.\n
  • Capability inventory: The agent has the capability to write analysis reports to the local file system.\n
  • Sanitization: There is no evidence of filtering or sanitization of external review content before it is processed for thematic analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 11:39 PM
Security Audit — agent-trust-hub — reputation-reviews