travis-ci-docs

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the runtime to use WebFetch to load arbitrary pages from docs.travis-ci.com (public web content), whose extracted text is then fed into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to use WebFetch at runtime to load and inject documentation from https://docs.travis-ci.com/user/ into the agent's context to answer queries, which is a runtime fetch of external content that will directly influence agent outputs.