agent-browser
Fail
Audited by Snyk on Feb 16, 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 examples and commands that embed credentials and secrets directly into CLI arguments and commands (e.g., fill @e2 "password123", --proxy http://user:pass@proxy..., set credentials user pass, cookies/storage set), which would require the LLM to handle or output secret values verbatim.
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 and scrapes arbitrary public URLs via commands like "agent-browser open ", "agent-browser snapshot", and "agent-browser get text/get html" (see the "导航", "快照", and "内容抓取" sections), which causes the agent to ingest untrusted third‑party web content that could carry indirect prompt injections.
Audit Metadata