cmux-team-gh

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute specific CLI commands, including cmux-team and gh, to retrieve and manage GitHub issue and pull request data.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to read and process untrusted external data from GitHub. Ingestion points: GitHub issue and pull request titles, bodies, and comments. Boundary markers: None specified in the instructions to isolate untrusted data from the agent's prompt context. Capability inventory: Subprocess execution via cmux-team and gh CLI tools. Sanitization: No measures for sanitizing or validating the content fetched from GitHub are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 07:00 AM
Security Audit — agent-trust-hub — cmux-team-gh