test-case-review
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data sources such as PRD (Product Requirement Documents), requirement models, and source code repositories to establish testing baselines.
- Ingestion points: Step 1 and Step 4 involve reading existing test case files, PRD/requirement models, and code repositories provided by the user.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the untrusted content or warn the agent to ignore instructions embedded within the processed documents.
- Capability inventory: The skill has the capability to perform file write operations (Step 5: "directly revise test case files") and execute local scripts.
- Sanitization: The instructions do not specify any validation, filtering, or escaping mechanisms for the data retrieved from external files before it is used to generate or revise content.
- [COMMAND_EXECUTION]: The workflow incorporates the execution of a local Python script for schema verification.
- Evidence: Step 5 explicitly requires the agent to use
../core/scripts/validate_schema.pyto re-verify the schema before saving the revised test case files.
Audit Metadata