amazon-review-intelligence-extractor

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its 'Insufficient Data Fallback' workflow.
  • Ingestion points: Raw Amazon reviews are fetched using the reviews-raw subcommand (stored in $WORK/raw.json) and subsequently processed by the agent to extract sentiment and thematic tags.
  • Boundary markers: The review content is wrapped in triple quotes ("""{text}""") within the render_review_map_prompt template to provide some structural separation.
  • Capability inventory: The agent can execute shell commands via a local Python script, perform network requests to the vendor's API, and write to the local file system.
  • Sanitization: The raw review text is interpolated into the prompt without explicit sanitization or filtering of adversarial instructions that might be embedded in the customer feedback.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled Python utility (scripts/zoodata.py) to handle API authentication, data retrieval, and local aggregation tasks.
  • [EXTERNAL_DOWNLOADS]: The Python script performs network operations to api.zoodata.ai to retrieve market data, product specifications, and customer reviews. This is a vendor-owned resource associated with the author 'SerendipityOneInc'.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 12:03 PM
Security Audit — agent-trust-hub — amazon-review-intelligence-extractor