gate-testcov
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or sensitive data access was detected. The skill is limited to high-level instructional prompts for generating test coverage.\n- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts, binaries, or configuration files that could execute code in the agent's environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes project code provided by the user. Ingestion points: '项目代码' (Project code) input. Boundary markers: Absent. Capability inventory: Code generation (writing E2E tests). Sanitization: Absent. This is a standard surface for code-processing utilities and does not indicate malicious intent.
Audit Metadata