netl-edx

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly falls back to asking the user for a NETL EDX API key and shows header/curl examples that embed the key (e.g., "EDX-API-Key: YOUR_KEY" or using a user-provided key), so an agent may need to receive and then output the secret verbatim, creating exfiltration risk despite recommending env vars/credentials files.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries and ingests dataset metadata and files from the public NETL EDX CKAN API (https://edx.netl.doe.gov/api/3/), including dataset "notes", "extras", and resources[].url as part of the required workflow (see SKILL.md steps for package_search/package_show and resource downloads), so it consumes untrusted third-party content that could contain instructions influencing agent actions.