qa-plan-creator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to populate plan templates, creating a surface where malicious content could influence the agent or be persisted in generated documents.
- Ingestion points: User-provided project name, scope, and dates as defined in the
Workflowsection ofSKILL.md. - Boundary markers: None; templates in the
references/directory (e.g.,test-plan.md,sprint-plan.md) use simple placeholders like[Project name]without explicit delimiters or instructions to ignore embedded instructions. - Capability inventory: The skill writes generated plans to the
docs/plansdirectory and integrates with theqa-diagram-generatorskill to produce Gantt charts. - Sanitization: No validation or escaping of user-supplied text is performed before interpolation into the output templates.
Audit Metadata