eve-web-ui-testing-agent-browser

Warn

Audited by Snyk on May 12, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to open and interact with arbitrary external URLs (e.g., agent-browser open in SKILL.md and references/commands.md) and the templates (templates/capture-workflow.sh, templates/form-automation.sh, references/proxy-support.md) show fetching public web pages and extracting/using page text and snapshots (agent-browser get text, snapshot -i) to drive subsequent actions, so untrusted third-party content can materially influence tool behavior.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 03:04 PM
Issues
1