analyzing-browser-forensics-with-hindsight

Warn

Audited by Snyk on Mar 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly ingests and analyzes browser profile artifacts (History, Cookies, Web Data and optional cache) from user browser profiles—see SKILL.md (commands including --cache and the "Upload or point to browser profile directory" web UI) and scripts/agent.py which read the History/Cookies/Web Data SQLite files—and uses that untrusted, public web content (visited URLs, cached pages, downloads) to flag suspicious sites and drive findings, so third‑party content can materially influence behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 12:27 AM
Issues
1