browser
Fail
Audited by Snyk on Mar 6, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to fill form fields by providing the exact text (e.g., browser(action="fill", ref="e2", text="...")) and explicitly notes the agent may "fill credentials," which forces the LLM to include secret values verbatim in its generated actions/commands.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's browser(action="navigate", url=...) and browser(action="snapshot") workflow (see SKILL.md "navigate" and "snapshot" sections and Core Workflow) explicitly fetches and reads arbitrary web pages as untrusted external content, which the agent is expected to interpret and act on (filling/clicking), enabling indirect prompt-injection from public third-party pages.
Audit Metadata