linkfox-amazon-reviews-list
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
amazon_reviews.py,onboarding.py) to interact with APIs and manage local data. It also includes instructions for the agent to guide users in modifying shell configuration files (e.g.,.zshrc,.bashrc) and usingsetxon Windows to store API keys persistently. - [PROMPT_INJECTION]:
- Ingestion points: The skill retrieves and processes Amazon product reviews from the API response at
amazon/reviews/list(handled inscripts/amazon_reviews.py). - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore potential commands embedded within the retrieved review text.
- Capability inventory: The agent can execute local scripts, write files to the project directory, and perform network requests to vendor APIs.
- Sanitization: Absent; the review content is presented to the agent without filtering or escaping potential malicious instructions.
- [EXTERNAL_DOWNLOADS]: The onboarding script and documentation guide the user to install well-known third-party Python packages (
requests,qrcode,pillow) for authentication and QR code rendering purposes. - [DATA_EXFILTRATION]: The skill performs network operations to vendor-owned domains (
tool-gateway.linkfox.com,api.linkfox.com,agent-api.linkfox.com) to retrieve product data and manage user authentication.
Audit Metadata