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 explicit examples that place plaintext secrets into commands (e.g., fill @e2 "password123") and exposes commands like get value that would return input contents, which forces the LLM to handle and emit 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 web pages (e.g., "agent-browser open" / "browser_navigate" and extraction commands like "browser_snapshot" and "browser_evaluate", including web‑scraping/infinite‑scroll social feed examples), so the agent will read and interpret untrusted, user‑generated third‑party content that could carry indirect prompt injection.
Audit Metadata