vitest-midscene-e2e

Warn

Audited by Snyk on Mar 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly clones and uses a public GitHub boilerplate via scripts/clone-boilerplate.sh (https://github.com/web-infra-dev/midscene-example.git) and instructs downloading https://midscenejs.com/llms.txt as part of lookup, and the agent is required to read/compare and copy those third-party files as authoritative project state—which could let untrusted external content influence its actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 19, 2026, 04:15 PM
Issues
1