reputation-sentiment
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: Reads review text from external websites via
WebSearchandWebFetchtools (SKILL.md). - Boundary markers: None identified.
- Capability inventory: Performs file writes to the local directory to save analysis reports.
- Sanitization: No explicit sanitization or filtering of review content is defined before processing or report generation.
Audit Metadata