cyrus-setup

Warn

Audited by Snyk on Mar 21, 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). The SKILL.md explicitly instructs the agent to use browser automation (claude-in-chrome or agent-browser) to navigate and scrape content from third-party web UIs (Linear, Slack, GitHub) and to extract/fill credentials as part of the setup, which exposes the agent to untrusted external web content that can influence its actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 11:48 PM
Issues
1