The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The installation section suggests a command that downloads and executes a shell script directly from a remote URL: curl -fsSL https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh | bash. This 'pipe to shell' pattern is dangerous because it executes unverified code with the user's privileges.
[EXTERNAL_DOWNLOADS]: The skill references and installs software from several external package managers and repositories, including Homebrew (xdevplatform/tap/xurl), NPM (@xdevplatform/xurl), and GitHub (github.com/xdevplatform/xurl).
[PROMPT_INJECTION]: The skill processes untrusted data from the X API, making it vulnerable to indirect prompt injection where malicious content in tweets or messages could influence the agent's behavior.
Ingestion points: Data returned from search, read, mentions, timeline, and dms commands.
Boundary markers: Absent. There are no instructions to the agent to treat API output as untrusted or to wrap it in delimiters.
Capability inventory: The tool has broad capabilities to post, reply, follow, block, and send DMs, which could be abused if an injection is successful.
Sanitization: Absent. The skill does not suggest any filtering or validation of the text content returned from the API.

xurl