ordercli
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the third-party
orderclitool from a non-standard GitHub repository (steipete/ordercli) using Homebrew or Go during the setup phase. - [COMMAND_EXECUTION]: Executes shell commands via the
orderclibinary to manage logins, sessions, and food orders. This includes high-privilege operations such as importing Chrome browser cookies and accessing local application support folders to bypass bot protection. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external food delivery APIs and restaurant menus.
- Ingestion points: Fetches active order status, order history, and restaurant details from external Foodora and Deliveroo APIs (
SKILL.md). - Boundary markers: No specific delimiters or boundary markers are defined to isolate external API data from the agent's instructions.
- Capability inventory: The skill can execute external binaries, read/write configuration files, access browser session data, and perform financial transactions (reordering) (
SKILL.md). - Sanitization: There is no evidence of sanitization or validation of the data retrieved from external sources before it is interpreted by the agent.
Audit Metadata