peekabo

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow and the CLI reference explicitly instruct running "peekaboo see --app 'Safari' --json-output" and then acting on captured UI elements (click/type/scroll), which means the agent ingests arbitrary content displayed in a browser (potentially untrusted public web pages) that can influence its subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 10:57 AM