agent-browser
Fail
Audited by Snyk on Feb 27, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt includes many examples and commands that embed secrets verbatim (e.g., fill with "password123", proxy URLs with user:pass,
set credentials user pass,cookies set name value), which instructs the agent to output or reproduce plaintext credentials directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to arbitrary URLs and ingests page content (e.g., SKILL.md's "agent-browser open ", snapshot/get text commands and the templates like templates/capture-workflow.sh which call agent-browser open $TARGET_URL and agent-browser get text body), so the agent will fetch and interpret untrusted public web content as part of its workflow.
Audit Metadata