restaurant-respond

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted restaurant reviews from external sources, creating a surface for indirect prompt injection where malicious content in a review could attempt to influence agent behavior.
  • Ingestion points: Reads review content from the local file RESTAURANT-REVIEWS-[Name].md or fetches them via WebSearch.
  • Boundary markers: None. The skill does not use specific delimiters or instructions to ignore potential commands within the review text.
  • Capability inventory: The skill possesses file-read and file-write capabilities (outputting to RESTAURANT-RESPONSES-[Name].md) and can perform WebSearch.
  • Sanitization: There is no explicit sanitization, validation, or escaping of the ingested review text before it is processed.
  • [SAFE]: No evidence of malicious command execution, unauthorized data exfiltration, credential harvesting, or obfuscation was detected in the skill contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 12:03 PM
Security Audit — agent-trust-hub — restaurant-respond