jb-test-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed exclusively of markdown documentation and natural language instructions. It does not include any scripts, binaries, or configuration files that execute automatically.
- [SAFE]: No network operations, data exfiltration attempts, or credential-handling patterns were detected. References to external repositories are provided solely for documentation and attribution.
- [SAFE]: The skill includes explicit safety guardrails for the agent, such as requiring authorization before committing or pushing changes and advising against editing code while test runners are active.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and modify repository content (code and tests). While this creates an ingestion surface for potentially untrusted data, this is the intended primary purpose of the tool in a development context. The skill provides a structured workflow with validation steps and human-in-the-loop authorization requirements to mitigate risks.
Audit Metadata