agent-browser
Fail
Audited by Snyk on Feb 15, 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 and exemplifies placing plaintext credentials directly into CLI commands (e.g., agent-browser fill @e2 "password123") and saving session state, which would require the LLM to emit secrets 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 arbitrary public URLs with commands like "agent-browser open " and extracts page content via "snapshot", "get text", and similar commands (e.g., the form example using https://example.com/form), so the agent will ingest untrusted, user-generated third-party web content that could carry indirect prompt injections.
Audit Metadata