The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The installation instructions suggest running curl -fsSL https://raw.githubusercontent.com/xdevplatform/xurl/main/install.sh | bash. This pattern downloads and executes a script directly from an external source with full shell privileges, posing a significant risk of remote code execution if the source is compromised or untrusted.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the X API, creating a vulnerability surface where malicious instructions embedded in tweets or messages could influence agent behavior.
Ingestion points: Data enters the agent context through commands such as xurl search, xurl timeline, xurl mentions, xurl read, and xurl dms (SKILL.md).
Boundary markers: Absent. The instructions do not provide specific delimiters or warnings for the agent to isolate or ignore instructions contained within the text fields of API responses.
Capability inventory: The skill grants the agent extensive write capabilities, including post, reply, dm, follow, and block (SKILL.md).
Sanitization: Absent. There is no mention of filtering or escaping content retrieved from the X API before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill refers to several external resources for installation and code acquisition, including a shell script on GitHub, the npm package @xdevplatform/xurl, and the Go package github.com/xdevplatform/xurl. These resources originate from the xdevplatform organization, which is not verified as a trusted vendor in the current environment.
[COMMAND_EXECUTION]: The skill is centered around the execution of the xurl CLI tool and various shell commands for setup, authentication, and API interaction, which involves spawning subprocesses for system and network operations.

xurl