agent-browser
Fail
Audited by Snyk on Mar 3, 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 demonstrates filling password fields with literal plaintext (e.g., agent-browser fill @e2 "password123") and saving/loading auth state, which would require the agent/LLM to include secret values verbatim in commands, creating an exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to navigate and ingest arbitrary public web pages (e.g., "agent-browser open ", "agent-browser snapshot -i", "agent-browser get text @e1" and "agent-browser wait --text ..."), so the agent will fetch and interpret untrusted third‑party content from arbitrary URLs as part of its workflow and that content can change subsequent interactions.
Audit Metadata