skills/clawlink-hq/skills/gorgias/Gen Agent Trust Hub

gorgias

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the @useclawlink/cli tool using npx to perform login, connection, and action tasks within Gorgias.
  • [CREDENTIALS_UNSAFE]: The documentation identifies that credentials will be stored at ~/.clawlink/credentials.json. This is a standard practice for CLI applications to manage user tokens locally and does not involve hardcoding secrets.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the download of the @useclawlink/cli package from the public NPM registry at runtime via npx commands.
  • [PROMPT_INJECTION]: The skill processes data from Gorgias (e.g., support tickets) which may contain untrusted content from external users, creating a surface for indirect prompt injection. Ingestion points: Gorgias ticket data; Boundary markers: Absent; Capability inventory: Shell command execution; Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — gorgias