kelly-products
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses well-established patterns for local and remote data management, employing environment variables for credentials and providing clear boundaries between data viewing and action execution.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data sources such as marketplace exports.
- Ingestion points: scripts/ingest_products.mjs reads a JSON payload containing product and channel data.
- Boundary markers: All sensitive operations are gated by a human approval process in the review queue.
- Capability inventory: The agent can perform channel publishing, price changes, and SKU archiving after receiving approval.
- Sanitization: Seller profile data is sanitized before display.
- [COMMAND_EXECUTION]: Utility scripts like ingest_products.mjs and execute_decisions.mjs are included for the agent to manage its internal Busabase data layer and record decisions. These scripts perform operations within the intended administrative scope of the skill.
Audit Metadata