empjs-skill

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs constructing and executing eskill commands that install skills from external sources (e.g., "eskill install https://github.com/..." and NPM/Git URLs), meaning the agent will fetch and install arbitrary public third-party repositories whose user-generated content could change agent behavior.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill maps user requests to runtime commands like "eskill install https://github.com/steelan9199/wechat-publisher/tree/main/skills" which cause the agent to fetch and install remote GitHub-hosted skill code that can execute code or control agent prompts, so the GitHub URL is a runtime external dependency that directly controls behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 08:13 PM