stelow-product-marketplace-playbook
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill contains strategic guidelines and documentation for marketplace management. It follows platform conventions for workflow integration and does not execute sensitive commands or access private data.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface where external market research is used to inform strategy selection. This is a standard operational pattern for this type of agent skill and is evaluated as safe given the lack of dangerous capabilities.
- Ingestion points: Results from external web research queries via the web-research.md contract.
- Boundary markers: None present in the playbook instructions.
- Capability inventory: Strategic text generation and local workflow state management via the scripts/stelow router.
- Sanitization: No specific sanitization methods for ingested market data are outlined.
Audit Metadata