csat-followup

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the composio CLI to perform specific actions like searching for tools, listing tickets from Gorgias, and sending emails via Gmail. These operations are restricted to the intended business logic of the skill and do not involve the execution of arbitrary or unverified shell commands.\n- [PROMPT_INJECTION]: The skill processes untrusted data from Gorgias tickets (such as customer names and issue subjects) to generate email drafts. While this presents an indirect prompt injection surface, the risk is mitigated by Step 5, which requires the agent to present all drafts to the user for manual confirmation and selection before any network activity (GMAIL_SEND_EMAIL) occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — csat-followup