The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown instructions and metadata. It does not include any Python scripts, Node.js code, or shell commands, which eliminates common attack vectors like remote code execution or persistence.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-supplied prose. While this represents a data ingestion surface, the skill lacks any 'write' capabilities (such as file system modification, network requests, or subprocess execution). Consequently, even if malicious instructions were embedded in the input data, the agent would have no dangerous tools to execute.
[SAFE]: No malicious patterns, obfuscation, credential harvesting, or unauthorized privilege escalations were detected. All external links point to the official repository of the skill author (OpenHands).

simplified-technical-english