scenario
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a structured planning framework for identifying adversarial scenarios. It does not exhibit any malicious patterns such as prompt injection, obfuscation, or unauthorized command execution.
- [DATA_EXPOSURE_PREVENTION]: The instructions include explicit safeguards against the exfiltration or storage of sensitive data, stating 'Never put secrets, real payment data, tokens, or personal data in scenario/evidence artifacts.'
- [INDIRECT_PROMPT_INJECTION_SURFACE]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from project files (e.g.,
product-roadmap.md,project-config.json) and user arguments ($ARGUMENTS). - Ingestion points: Reads local documentation files and user-supplied context to generate scenarios.
- Boundary markers: Uses
<request>$ARGUMENTS</request>tags to isolate user input. - Capability inventory: Limited to reading local documentation, querying the user via the
ask user question tool, and writing analysis reports to the local filesystem. - Sanitization: Includes warnings to the model to redact sensitive information from outputs.
Audit Metadata