wds-3-scenarios
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external artifacts such as the Product Brief and Trigger Map which could theoretically contain malicious instructions designed to influence agent behavior.
- Ingestion points: Files including product-brief.md, trigger-map.md, and existing scenario outputs are read in steps-c/step-01-load-context.md and steps-v/step-01-scenario-coverage.md.
- Boundary markers: The skill utilizes a highly structured 8-question dialog and explicit templates (scenario-outline-template.md) to constrain output generation.
- Capability inventory: The skill is limited to reading and writing local project files within the specified output directory.
- Sanitization: The workflow includes several mandatory user checkpoints in steps 02, 04, and 05, alongside a dedicated quality review in step 07, which mitigate the risk of unintended instruction execution.
Audit Metadata