qa-planning
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes requirements and user context to generate risk matrices and test designs. This creates a surface for indirect prompt injection, where malicious instructions in the requirements could potentially influence the agent's output.
- Ingestion points: Requirements analysis and user context gathering in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: File system write access for report generation and user interaction.
- Sanitization: No explicit sanitization or validation of input data.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script to manage file naming conventions for generated reports.
- Evidence: Sourcing and executing functions from 'references/newest-numbered.sh' as described in the SKILL.md configuration section.
Audit Metadata