ticket-triage

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via bash to interact with the composio CLI. These commands are used to search for tools, fetch schema information, and perform data operations like listing and retrieving details for support tickets from the Gorgias platform.
  • [PROMPT_INJECTION]: The skill ingests and analyzes customer-provided support ticket content, which represents an attack surface for indirect prompt injection. Maliciously crafted ticket content could attempt to influence the agent's triage decisions or priority assignments.
  • Ingestion points: Message threads retrieved from Gorgias via the GORGIAS_GET_TICKET tool.
  • Boundary markers: The instructions do not define specific delimiters or guardrails to isolate ticket content from the analysis prompts.
  • Capability inventory: The skill has the ability to execute shell commands (bash) and use the composio toolkit.
  • Sanitization: There is no evidence of content filtering or validation performed on the external data before it is processed for triage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — ticket-triage