chef

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md shows the skill actively ingests free-text Telegram user messages (e.g., chef.ask(), chef.collect(), chef.confirm(), chef.choice()) — untrusted user-generated content the agent reads and can materially influence its next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:11 PM