agent-browser
Fail
Audited by Snyk on Feb 17, 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's examples and workflows explicitly show filling inputs with literal credentials (e.g., agent-browser fill @e2 "password123"), which requires the agent to include secret values verbatim in generated commands/outputs.
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 URLs with "agent-browser open " and ingests page content via "agent-browser snapshot -i --json" (examples include scraping news.ycombinator.com), so the agent will fetch and parse untrusted public web content that could carry indirect prompt injections.
Audit Metadata