wechat-2d-render

Warn

Audited by Snyk on Nov 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The workflow clones and updates a public GitHub repository (sxhzju/wechat-2d) and then runs its install and render scripts, so content from that public repo reaches the agent's runtime even though it is mostly code the agent executes rather than prose it reads.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill clones https://github.com/sxhzju/wechat-2d, a personal individual-owned repository with no first-party or authenticated provenance, then runs pnpm install and its Remotion scripts, so it executes unverified remote code from a common but unofficial source (medium).

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's only environment change is corepack enable pnpm, a global tooling change, and it shows no irreversible operational loss, so the tier is low.

Issues (3)

W011
MEDIUM

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

W012
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 21, 2026, 01:17 AM
Issues
3