mcp-tokenflux-images

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Suspicious: the skill explicitly tells users to curl and pipe a raw .sh from an unverified GitHub repo (vaayne/mcphub)—a direct remote-execution vector—and references an unknown domain (tokenflux.ai) as the API endpoint, both of which are common vectors for distributing malware.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to call the TokenFlux API (https://tokenflux.ai/v1/images/mcp) and specifically to use getModel to fetch a model's input_schema from the third-party service, which the agent is expected to read and use to construct generateImage requests—allowing untrusted/malicious schema content to influence tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's required-install instruction runs remote code via curl -fsSL https://raw.githubusercontent.com/vaayne/mcphub/main/scripts/install.sh | sh, which fetches and executes a script and is presented as a required dependency for runtime use.