agent-browser
Fail
Audited by Snyk on Mar 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 prompt contains multiple examples that embed plaintext credentials or session tokens directly into commands and state files (e.g., fill "password123", saving/using state files with plaintext tokens, piping echo "pass"), which would require an LLM to emit secret values verbatim and thus creates an exfiltration risk despite also offering safer alternatives.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates and scrapes arbitrary public URLs (see SKILL.md commands like "agent-browser open ", "agent-browser snapshot -i", "agent-browser get text body") and the provided templates (templates/capture-workflow.sh, form-automation.sh, templates/authenticated-session.sh) show the agent ingesting page content and using it (refs/text) to drive actions, so untrusted third-party page content can materially influence agent decisions and tool use.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata