agent-browser
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt includes examples and commands that place secrets directly into CLI arguments and command outputs (e.g., fill @e2 "password123", set headers '{"X-Key":"v"}', set credentials user pass, cookies set name value), which requires the LLM to handle and emit secret values verbatim.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to arbitrary webpages using "agent-browser open " (Core workflow and examples) and then snapshots, reads (get text/get html), and interacts (click/fill/eval) with page content, so untrusted public web pages can be ingested and materially influence the agent's actions.
Audit Metadata