agent-browser-5
Fail
Audited by Snyk on Mar 4, 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 commands and examples that embed plaintext secrets/credentials verbatim (e.g., fill @e2 "password123", agent-browser set credentials user pass, set headers '{"X-Key":"v"}'), which would require the LLM to output secret values directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to navigate to arbitrary URLs (agent-browser open ) and to snapshot/read page content (agent-browser snapshot, get text/get html, eval), meaning it fetches and interprets untrusted public web pages whose content can influence subsequent actions.
Audit Metadata