linkfox-zhihuiya-patent-forward-citation

Fail

Audited by Snyk on Jul 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.


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 runtime API response (citedOthers / citedPatents fields) returned by POST /zhihuiya/patentForwardCitation, which the script prints to stdout (full JSON when --inline or response ≤ 8KB, otherwise a summary that still includes samples), and that stdout is typically ingested 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's runtime remediation step explicitly directs downloading and installing remote code from https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip (a release ZIP for the linkfox-onboarding skill), which would fetch remote code that could be executed or alter agent behavior.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 16, 2026, 08:11 AM
Issues
3