whatsapp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to copy the QR authentication block into its reply (and the daemon can "return the QR inline"), which requires the LLM to include an ephemeral authentication token/secret verbatim in its output, creating an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Contains a curl of a raw GitHub-hosted shell script from an unverified/unknown user and a direct "curl | sh" install instruction in scripts/start.sh, which is a high-risk pattern for distributing malware.