ecommerce-amazon-policy-feed

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches Amazon policy and regulation data from an external API and instructs the agent to render the content (Markdown) "as-is" in the detail view. This creates a surface where malicious instructions embedded in the policy feed could influence the agent's behavior.
  • Ingestion points: Data is fetched via call_api in scripts/amazon_policy_feed.py and scripts/amazon_policy_feed_detail.py.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the fetched content.
  • Capability inventory: The scripts have the ability to write files to the local project directory and the user's home directory, and perform network operations via urllib.
  • Sanitization: There is no evidence of sanitization or validation of the Markdown content returned by the API before it is output to the agent.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to an external API endpoint defined by the NEXSCOPE_PROXY_BASE environment variable to retrieve the policy feed and article details. These resources are managed by the skill's vendor (nexscope-ai).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:13 AM
Security Audit — agent-trust-hub — ecommerce-amazon-policy-feed