xurl
Fail
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides installation commands that download and execute a shell script directly from the official X developer platform repository on GitHub.
- [COMMAND_EXECUTION]: The skill executes a local PowerShell script (install_xurl_windows_shim.ps1) and utilizes the xurl CLI for account management and content operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (Twitter) such as search results, mentions, and direct messages, creating a surface for potential injection attacks. Ingestion points: xurl search, xurl timeline, xurl mentions, and xurl dms. Boundary markers: No specific delimiters or safety instructions are defined to wrap the external data. Capability inventory: Significant write access including posting, messaging, and account social graph management. Sanitization: No explicit content filtering or validation of ingested data is documented.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh - DO NOT USE without thorough review
Audit Metadata