qa-validation-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via 'npm run' for type-check, lint, test, and build operations. These are standard software development tasks and are consistent with the skill's primary function of quality assurance validation.
- [PROMPT_INJECTION]: The workflow involves reading and processing external data from 'prd.json', GDD documents, and project source files. This represents an indirect prompt injection surface as these files could contain malicious instructions designed to alter the agent's behavior during validation or refactoring.
- Ingestion points: Requirements are ingested from 'prd.json' and GDD specification files, and source code is read from the files listed in the validation request.
- Boundary markers: The instructions do not define delimiters or provide specific warnings for the agent to ignore instructions embedded within the ingested data.
- Capability inventory: The skill has the capability to run local shell commands via npm and to trigger a subagent with code modification privileges.
- Sanitization: There is no evidence of sanitization or validation performed on the contents of the ingested files before they are processed by the agent or passed to subagents.
Audit Metadata