crm-management
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file instructs the agent to perform a local file system check using the
lscommand on standard skill directories (e.g., ~/.claude/skills/, ~/.agent/skills/) upon activation. This is intended to identify and recommend missing companion skills provided by the same vendor.\n- [PROMPT_INJECTION]: The skill mandates that the agent always begins its first response with a 🧢 emoji. This is a stylistic behavioral constraint that does not attempt to subvert safety filters or override core agent instructions.
Audit Metadata