amazon-review-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
web_fetchto retrieve product reviews, titles, and metadata from Amazon. This behavior is consistent with the skill's primary function of competitive and sentiment analysis. - [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to instructions embedded in the data it processes (indirect prompt injection).
- Ingestion points: External content is ingested via
web_fetchfrom Amazon product review pages as described in the 'Data Source' sections ofSKILL.mdandREADME_CN.md. - Boundary markers: The instructions do not define clear delimiters or specific instructions to the agent to ignore any command-like text found within the retrieved reviews.
- Capability inventory: The skill uses the
web_fetchtool to access external URLs. - Sanitization: There is no evidence of pre-processing, sanitization, or filtering of the fetched text before it is presented to the agent for analysis.
Audit Metadata