job-post-writer

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions do not contain any attempts to override safety filters, bypass constraints, or extract system prompts. The language is purely instructional and task-oriented.
  • [DATA_EXFILTRATION]: There are no patterns suggesting the collection or unauthorized transmission of sensitive data. The skill operates on user-provided job descriptions and business details to generate output.
  • [REMOTE_CODE_EXECUTION]: The skill does not include any commands to download, install, or execute remote scripts or packages.
  • [COMMAND_EXECUTION]: While the 'Bash' tool is included in the frontmatter, the instructions do not contain any shell commands or requests for the agent to execute arbitrary system operations.
  • [EXTERNAL_DOWNLOADS]: The skill uses 'WebSearch' specifically to verify state-level pay transparency laws, which is a legitimate and safe use of the tool for its stated purpose. No other external resources are referenced.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — job-post-writer