jiekou-docs

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to use WebFetch to read external reference documentation from GitHub repositories, which constitutes low-risk exposure to fetched content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to dynamically fetch remote markdown reference files from raw.githubusercontent.com during execution, constituting a weak/unknown/suspicious runtime external dependency.