complexity-check

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains an optional feedback reporting section using an external npx command with an unverified third-party endpoint.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (medium risk: 0.30). The skill contains a command that executes an npx package download from hivenet@latest, representing an operational software download from a third-party source.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an operational feedback command that executes a remote package download from hivenet.app (hivenet@latest) with a DSN URL, which introduces an unverifiable runtime external dependency.