agent-browser

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The skill’s examples and command patterns show credentials embedded verbatim in CLI calls (e.g., agent-browser fill @e2 "password", --headers ), which requires the LLM to output secret values directly and thus poses an exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly opens arbitrary web pages (agent-browser open ) and returns structured snapshots via "agent-browser snapshot -i --json" so the agent ingests accessibility trees/JSON from public websites, exposing it to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:30 PM