plain-portal

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires the agent to read or ask for a portal code (a secret/session token) and embed it verbatim into connection commands (uv run plain portal connect ), which exposes secrets in the agent's output — a direct exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill provides an explicit remote Python shell and encrypted tunnel that allows arbitrary remote code execution and file transfer (including pulling arbitrary remote files and enabling writable sessions), which creates clear backdoor-like access and direct avenues for data exfiltration and credential theft—high risk for abuse.