oodle-discovery

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for API credentials and to pass them inline as environment-variable assignments in shell commands (e.g., DD_API_KEY=...), which requires the LLM to include secret values verbatim in generated commands/outputs.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Most URLs point to official package hosting (files.pythonhosted.org) or well-known GitHub/npm providers and are low-risk, but the direct shell install script (astral.sh) and a URL containing embedded credentials (admin:s3cret@...) are risky: running a remote install.sh via curl|sh can deliver arbitrary code, and credentials-in-URL exposes secrets and may leak privileged access.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly offers to install a required runtime tool by executing remote code via "curl -LsSf https://astral.sh/uv/install.sh | sh", which fetches and runs a script at runtime (https://astral.sh/uv/install.sh).