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 instructs embedding JWT cookie values directly into CLI commands (e.g., cookies set "eyJhbG..."/export AUTH_HEADER), which requires the agent to read and output secret token values verbatim, creating 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 open arbitrary URLs (e.g., "npx agent-browser open " and "npx agent-browser diff url ") and to snapshot/inspect page DOM and interact with elements (click/fill/get text/eval), which means untrusted public web content can be fetched and directly drive agent actions and decisions.
Audit Metadata