ajtbd-recruit
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security risks were identified. The skill adheres to its stated research-oriented purpose.- [PROMPT_INJECTION]: The instructions are clear and task-specific, containing no attempts to override safety filters, bypass constraints, or extract system prompts.- [EXTERNAL_DOWNLOADS]: The skill references established recruitment platforms and agencies (e.g., LinkedIn, UserInterviews, Respondent.io) as informational resources. It does not perform automated downloads or execution of external scripts.- [COMMAND_EXECUTION]: While the 'Bash' tool is listed as an allowed capability in the skill metadata, the prompt logic is focused on file I/O and information synthesis, with no evidence of dangerous shell command execution.
Audit Metadata