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: 1.00). The skill's CLI examples and workflow show credentials passed directly as literal command arguments (e.g., agent-browser fill @e2 "password123"), which requires the LLM to embed secret values verbatim in its output.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The agent-browser skill can navigate to arbitrary public URLs with commands like "agent-browser open " and then extract page content via "snapshot", "get text", "get html", etc., so it ingests untrusted public web/user-generated content that could carry indirect prompt injection.
Audit Metadata