skills/gen-verse/openclaw-rl/ordercli/Gen Agent Trust Hub

ordercli

Warn

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the ordercli binary from an external GitHub repository (github.com/steipete/ordercli) using the Go toolchain or Homebrew.
  • [DATA_EXFILTRATION]: The skill provides commands to import and extract sensitive authentication cookies and session data from the user's Chrome browser profile, specifically via ordercli foodora cookies chrome and ordercli foodora session chrome.
  • [CREDENTIALS_UNSAFE]: The tool handles sensitive user credentials, including passwords via standard input and authentication tokens stored in environment variables like DELIVEROO_BEARER_TOKEN.
  • [COMMAND_EXECUTION]: The skill executes the ordercli binary and interacts with the host's filesystem, including the ~/Library/Application Support/ directory.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external food delivery APIs (order history, restaurant names) which represents a surface for indirect prompt injection, particularly as it lacks explicit boundary markers or sanitization for processed content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 02:37 AM