qa-test-plan
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command to ensure the output directory exists.
- Evidence:
mkdir -p {base_directory}/deliveryinSKILL.mdStep 5. - [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external data from requirements files which could contain malicious instructions designed to influence the agent's behavior during the test plan generation process.
- Ingestion points: The agent reads
business-requirements.yamlandtechnical-requirements.yamlfrom the user-specified or auto-detected{base_directory}/requirements/inSKILL.mdStep 1. - Boundary markers: There are no explicit instructions for the agent to ignore or delimit potentially malicious content within these requirements files.
- Capability inventory: The skill has the capability to create directories (
mkdir) and write files (qa-test-plan.yaml) to the file system. - Sanitization: The instructions do not specify any validation, filtering, or escaping of the content read from the external YAML files before they are used to generate the test suites and cases.
Audit Metadata