writing-job-descriptions
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions were found that attempt to override agent safety guidelines or extract system prompts. The instructions are focused on structured output for hiring tasks.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were detected.
- Unverifiable Dependencies (SAFE): The skill does not include any scripts or package management files (e.g., package.json, requirements.txt).
- Indirect Prompt Injection (SAFE): While the skill processes user-provided role descriptions, it lacks dangerous capabilities such as code execution or network transmission that could be exploited by malicious input data.
- Obfuscation (SAFE): No encoded strings, hidden characters, or deceptive formatting were found in the markdown files.
Audit Metadata