food-order-hardened
Warn
Audited by Snyk on Apr 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: 0.70). The skill's SKILL.md explicitly instructs the agent to use ordercli to interact with the public Foodora site (e.g., "ordercli foodora history --limit 10", "ordercli foodora history show --json", and "ordercli foodora session chrome --url https://www.foodora.at/"), meaning the agent will fetch and parse live, untrusted third‑party content (order history, addresses, menu data) that can materially influence subsequent tool actions like reordering.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata