amazon-data
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill performs GET requests to the official Canopy API domain (rest.canopyapi.co) to retrieve Amazon product information, search results, and metadata. This network activity is consistent with the skill's stated purpose and targets the vendor's own infrastructure.
- [CREDENTIALS_UNSAFE]: Authentication is handled via an API-KEY header. The skill provides examples for securely retrieving this key from environment variables (os.environ) and uses clear placeholders for setup instructions, preventing the hardcoding of secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from Amazon, such as product descriptions and customer reviews. This represents a potential indirect prompt injection surface.
- Ingestion points: SKILL.md (via requests to API endpoints for reviews and product details).
- Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling retrieved data.
- Capability inventory: The skill code is limited to data retrieval and does not include risky capabilities such as subprocess execution or file system modifications.
- Sanitization: No data sanitization or validation logic is included in the implementation examples.
Audit Metadata