omniroute-integration

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The prompt includes a persona that explicitly impersonates a real authority figure ("Sam Altman" with CEO/OpenAI credentials), which is a deceptive instruction to adopt an authoritative identity unrelated to the OmniRoute integration's stated purpose.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes explicit curl examples and instructions to add Authorization headers like -H "Authorization: Bearer your-key" and references JWT_SECRET/provider OAuth credentials, which encourages embedding user API keys/tokens verbatim in commands or outputs and thus enables secret exfiltration risk.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The prompt explicitly instructs privileged system operations (e.g., "sudo systemctl start/stop/status", "sudo journalctl -u ...", checking/repairing system database files and permissions) that modify service state and require sudo, so it encourages changing the machine's state.