edgespeak-broadcast

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly shows the pattern edgespeak-cli activate <KEY>, which encourages placing an activation key directly on the command line (and thus having the agent accept/echo a secret value verbatim), an insecure credential-handling pattern.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). This is a direct shell installer (install.sh) served from a third-party domain and the skill advises piping it into sh (curl ... | sh), which is a high-risk pattern for distributing malware if the host or content is malicious or compromised.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill tells users to run "curl -fsSL https://edgespeak.com/install.sh | sh" if the CLI is missing, which fetches and executes remote code at runtime (https://edgespeak.com/install.sh).