skills/zhinjs/plugins/link-poster/Gen Agent Trust Hub

link-poster

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill's functionality is limited to formatting external link information.
  • [NO_CODE]: The skill consists of instructions in SKILL.md only and does not include or reference external scripts or executable code.
  • [PROMPT_INJECTION]: The skill processes content from untrusted external URLs (Bilibili, GitHub, etc.) to generate preview cards. This represents an indirect prompt injection surface where malicious metadata in a link could attempt to influence the agent. (Ingestion points: Message links from supported social media platforms. Boundary markers: None specified. Capability inventory: Invokes the html-renderer plugin. Sanitization: None described.)
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 08:03 AM
Security Audit — agent-trust-hub — link-poster