codewiki

Warn

Audited by Snyk on Mar 7, 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's code and SKILL.md show it uses Puppeteer to fetch and scrape public CodeWiki pages (e.g., https://codewiki.google/github.com/[owner]/[repo] in codewiki.js getRepoDocumentation and getFeaturedRepos), extracting document.body/TOC/code links that the agent reads and uses to produce outputs, which exposes it to untrusted third‑party content that could carry injected instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 08:40 AM