review-response-writer

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to fetch and process review text from external sources using the WebFetch tool. An attacker could craft a malicious business review containing hidden instructions to override the agent's behavior. \n
  • Ingestion points: Untrusted data enters the agent context via the WebFetch tool (fetching from business profiles), user-pasted review text, or exported review files (SKILL.md). \n
  • Boundary markers: The instructions do not define delimiters or provide specific 'ignore embedded instructions' warnings to the agent for the untrusted content. \n
  • Capability inventory: The agent has access to the Bash, Write, Read, and WebFetch tools, providing a significant exploitation surface if a prompt injection is successful. \n
  • Sanitization: There is no evidence of input validation, escaping, or sanitization of the fetched review content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — review-response-writer