writing-unit-tests
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external project artifacts including code, requirement documents (TCO), and defect reports. These external sources could contain malicious instructions designed to influence the agent's behavior during the test generation or execution phases.
- Ingestion points: Project code, requirement documents, and defect reports (Section 1).
- Boundary markers: None explicitly defined to separate untrusted project data from instructions.
- Capability inventory: File system modification (creating/editing test files) and shell command execution (running tests in Section 5).
- Sanitization: No explicit sanitization or validation of the ingested project data is mentioned.
- [COMMAND_EXECUTION]: The skill requires the agent to identify and run shell commands for executing unit tests (e.g., "只运行目标测试并判定结果"). This capability allows the agent to execute potentially arbitrary commands found within the project's environment or configuration.
Audit Metadata