fast-browser-use

Fail

Audited by Snyk on Nov 22, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a browser automation tool whose advertised features (saving and reusing login sessions, scraping, and anti-detection flags) serve the user's own stated tasks, with no evidence of intent to attack or deceive the user; the "cookie heist" framing and stealth flags are sketchy enough to flag under the recall-first override.

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

  • Third-party content exposure detected (low risk: 0.10). The required runtime workflow navigates to agent- or user-selected URLs and extracts DOM, markdown, or text from arbitrary web pages (including the Hacker News and social-feed harvest examples), which is browser extraction of outsider-authored content that the agent must actively fetch, so the exposure is low rather than medium.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 22, 2026, 01:13 AM
Issues
2