amazon-seller-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, which presents a surface for indirect prompt injection.
- Ingestion points: As described in
SKILL.mdunder the 'Data Sources' section, the skill uses theweb_fetchtool to retrieve content from Amazon seller store pages and product detail pages, including titles, prices, and BSR rankings. - Boundary markers: The skill instructions do not provide specific delimiters or 'ignore' directives to prevent the agent from being influenced by malicious instructions that might be embedded in the fetched product descriptions or seller pages.
- Capability inventory: The agent uses
web_fetchfor data retrieval and performs complex analytical tasks (revenue estimation, strategy identification) based on the fetched data. - Sanitization: There is no evidence of sanitization, HTML stripping, or validation of the external content before it is processed by the language model's reasoning logic.
Audit Metadata