reputation-respond
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it fetches untrusted text from external websites and processes it directly into a generation task.\n
- Ingestion points: Phase 1 (Review Collection) uses WebSearch and WebFetch to retrieve content from external review sites.\n
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the retrieved review text.\n
- Capability inventory: The skill is designed to write content to local files (markdown responses). It does not request execution or administrative capabilities.\n
- Sanitization: There is no mechanism described for filtering or escaping instructions that might be contained within the reviews.\n- [EXTERNAL_DOWNLOADS]: The skill fetches review information from well-known services including Google, Yelp, and Trustpilot to perform its primary function.\n- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts or external dependencies.
Audit Metadata