inbox-zero

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes composio CLI commands in Bash to interact with the Gorgias platform for tool discovery and execution.
  • [EXTERNAL_DOWNLOADS]: Fetches ticket content and interacts with the Gorgias platform API through the Composio toolkit.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection:
  • Ingestion points: Untrusted customer messages are ingested from Gorgias tickets in SKILL.md.
  • Boundary markers: No delimiters or instructions are used to separate ticket content from agent instructions.
  • Capability inventory: The agent can execute write actions (reply, close, assign) via composio execute.
  • Sanitization: No sanitization is performed on ticket content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — inbox-zero