linkfox-zhihuiya-abstract-data-translated

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). The link to a direct ZIP archive (https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip…) is a high-risk distribution vector because it delivers an archive that may contain executables and is being distributed outside an official package manager; the other listed endpoints are API/docs on the linkfox domain and are not downloads.

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text is ingested from the runtime API response (data[].title / data[].abstractText) returned by POST /zhihuiya/abstractDataTranslated and then serialized/printed into the agent context (especially when --inline or response ≤ 8KB), so the LLM can read untrusted patent text from an external source.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's troubleshooting flow instructs the agent to download and install remote code from https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip at runtime to resolve onboarding/auth issues, which would fetch and install executable skill content that can control prompts or behavior.