test-case-review
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
../core/scripts/validate_schema.pyto validate the test case schema after revisions are made. This involves shell command execution within the agent environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as PRD documents and code repositories, which serves as a potential attack surface for indirect prompt injection.
- Ingestion points: Existing test case files, PRD/requirement models, and code repositories (referenced in the '工作流' and '输入' sections).
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the analyzed documents.
- Capability inventory: The skill possesses file system write capabilities (directly revising test case files in Step 5) and subprocess execution capabilities (running the Python validation script in Step 5).
- Sanitization: Absent; there is no mention of filtering or sanitizing content extracted from the PRD or code before it is used to influence the agent's review and revision logic.
Audit Metadata