write-reviews
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses the user's Amazon order history and product pages via the browser to verify purchase context. This is limited to the user's active browser session and is necessary for the skill's primary function of assisting with reviews for purchased items.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Amazon product pages and reviews).
- Ingestion points: Browser access to product pages and order history in
SKILL.md. - Boundary markers: Instructions require the agent to ground drafts in the user's specific experience and trade-offs.
- Capability inventory: Browser automation for form filling and submission.
- Sanitization: No explicit sanitization or filtering of web content is defined in the instructions.
- Risk Mitigation: The risk is significantly reduced by the mandatory requirement for explicit user confirmation before any content is submitted or actions are finalized.
Audit Metadata