jtbd-analysis
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): Instructions use natural language to define task-specific formatting constraints (e.g., Job Statement format) and do not attempt to override safety protocols or extract the system prompt.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or network communication patterns were detected.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill contains no code execution logic, package installations, or remote script fetches.
- [Indirect Prompt Injection] (LOW): The skill processes untrusted user data (interviews and product info). While it lacks explicit boundary markers to separate instructions from data, the skill has no dangerous capabilities (filesystem access, network access, or command execution) to exploit.
Audit Metadata