sales-playbook

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive audit of the skill's instructions, references, and evaluation prompts revealed no security vulnerabilities. The skill adheres to best practices and focuses on providing instructional sales content.
  • [COMMAND_EXECUTION]: The skill includes a prompt instruction for the agent to check the local filesystem for companion skills from the same vendor ecosystem.
  • Evidence: The 'Companion check' section in SKILL.md directs the agent to execute a directory listing (ls) on several common AI agent skill paths (e.g., ~/.claude/skills/).
  • Context: This action is intended to identify whether recommended related skills (like crm-management) are present, allowing the agent to provide a better setup experience to the user. This is a non-malicious use of the agent's shell capabilities and does not target sensitive user data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:05 PM
Security Audit — agent-trust-hub — sales-playbook