agent-browser

Fail

Audited by Snyk on Mar 7, 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 contains examples that embed plaintext credentials directly in CLI commands (e.g., agent-browser fill "password123") and instructs filling forms with user/password values, which would require the LLM to 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's core workflow (SKILL.md "Navigate: agent-browser open " and related examples/templates like templates/capture-workflow.sh and form-automation.sh) explicitly opens arbitrary public URLs and snapshots/gets page text and element refs, meaning the agent fetches and interprets untrusted web content which can change subsequent actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 7, 2026, 01:59 PM