first-hires-playbook

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local Python script, scripts/check-output.py, which is intended to be used as a deliverable validator. The script reads a file path provided as a command-line argument and checks for specific keywords. It does not perform network operations, access sensitive files, or attempt persistence.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context (e.g., company ARR, headcount, role requirements) to generate hiring plans, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is ingested through user input defined in the 'Output Format' section of SKILL.md and the templates/output-template.md file.
  • Boundary markers: The skill does not implement specific boundary markers or instructions to ignore embedded commands in the user-provided text.
  • Capability inventory: The skill includes a local file read capability via scripts/check-output.py.
  • Sanitization: No input sanitization is performed on the user-provided metrics or descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 12:46 PM
Security Audit — agent-trust-hub — first-hires-playbook