omnicaptions-LaiCut

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API key if not set and pass it via command-line arguments (-k <key>), which risks exposing the secret value in the agent's execution logs and context.

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

• Potentially malicious external URL detected (high risk: 0.70). The setup instructions install a package from an unofficial GitHub Pages Python package repository (https://lattifai.github.io/pypi/simple/), constituting an external runtime dependency with weak or unverified provenance.