writing-job-descriptions
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a well-defined workflow for hiring tasks without introducing technical risks. It defines inputs, outputs, and quality gates using markdown templates and checklists.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as role titles and team context. While it lacks explicit boundary markers (e.g., delimiters) or sanitization for this input, it has no dangerous capabilities (network access, file system writes, or command execution) that could be exploited via injection. The risk is negligible as it only produces text artifacts.
- [DATA_EXPOSURE_&_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file path access, or unauthorized network operations was found. The skill does not interact with the external environment.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or packages.
- [DYNAMIC_CONTEXT_INJECTION]: The
SKILL.mdfile does not utilize any dynamic shell execution syntax (!command).
Audit Metadata