linkfox-zhihuiya-description-data

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). Most URLs are API or vendor pages, but the line linking to a direct ZIP download (https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip…) is a direct archive distribution that could carry installers or executables and is therefore potentially high-risk.

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the tool’s runtime API response: scripts/zhihuiya_description_data.py calls POST /zhihuiya/descriptionData, then prints either the full JSON (--inline or small responses) or a summary that includes samples from data to stdout, which the agent may ingest as LLM-readable text.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's README instructs the agent at runtime to download and install an onboarding skill from https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip which would fetch and install remote code that can alter agent behavior, so this external URL is a runtime dependency that could control prompts/execution.