skills/manaflow-ai/cmux/cmux-backend/Gen Agent Trust Hub

cmux-backend

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructions direct the agent to access provider secrets from sensitive local file paths including ~/.secrets/cmux.env, ~/.secrets/cmuxterm-dev.env, and ~/.secret/cmuxterm.env to facilitate cloud VM builds and local development.
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines the creation of Vercel route handlers that ingest and parse data from external request inputs, which constitutes a potential attack surface.
  • Ingestion points: Request inputs are parsed at the boundary of route handlers within web/app/api/** and web/services/**.
  • Boundary markers: There are no instructions for using delimiters or explicit warnings to the agent to ignore instructions embedded in the external data.
  • Capability inventory: The agent is empowered to perform database writes (Postgres), manage Cloud VM lifecycles through provider APIs, and interact with authentication and pricing services.
  • Sanitization: The skill does not provide requirements for sanitizing, validating, or escaping the external request input before it is passed to Effect services.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 07:15 PM
Security Audit — agent-trust-hub — cmux-backend