amazon-competitor-monitoring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted external sources, specifically Amazon product pages and search engine results, which could theoretically contain malicious instructions.
- Ingestion points: Data is pulled into the agent's context through the
web_searchandweb_fetchtools in Steps 1, 2, and 3. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the external data.
- Capability inventory: The skill is limited to reading data via web tools and synthesizing reports. It does not possess capabilities for file-system modification, code execution, or network exfiltration.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the web pages before processing.
Audit Metadata