xurl
Fail
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs users to install the
xurlutility by piping a remote script directly to the bash interpreter (curl -fsSL https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh | bash). This pattern executes arbitrary code from an unverified external source without any local verification of the script content. - [EXTERNAL_DOWNLOADS]: The skill relies on external software distribution channels from an unverified organization (
xdevplatform). This includes a Homebrew formula (xdevplatform/tap/xurl), an npm package (@xdevplatform/xurl), and a Go module (github.com/xdevplatform/xurl@latest). - [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection (Category 8). It ingests untrusted data from the X API through several commands (e.g.,
read,search,mentions,timelineinSKILL.md). There are no boundary markers or sanitization procedures defined to prevent malicious text within social media posts from being interpreted as instructions by the agent. This is particularly risky as the agent has significant capabilities to write data (post, reply, DM, block) which could be triggered by such an injection.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata