research-archival

Warn

Audited by Snyk on Mar 1, 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 explicitly scrapes and ingests content from public third‑party sources (ChatGPT/Gemini/Claude share URLs and arbitrary web pages via the "Scraping Workflow" and references/url-routing.md using Firecrawl and Jina Reader) and then reads and incorporates that content into archived markdown and GitHub issue bodies, so untrusted user-generated pages could indirectly inject instructions that alter agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 06:55 AM