fetch-url

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt includes an example of passing a bearer token (tok_xxx) via a command line header flag, which encourages embedding sensitive credentials directly into commands.

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches arbitrary web pages selected by the agent, which represents an active search/fetch of outsider-accessible content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill executes an npm package via npx from an unverified third-party personal scope (@arabold), constituting a weak/unknown operational dependency.