The Agent Skills Directory

[SAFE]: The skill functions exclusively as a text generator. It lacks any functionality for file system access, network communication, or external command execution.
[INDIRECT_PROMPT_INJECTION]: The skill accepts external data such as URLs and user-provided text examples to match writing styles. Ingestion points: User-provided URLs and past post examples in SKILL.md. Boundary markers: No specific delimiters or safety instructions are used to isolate untrusted input. Capability inventory: No capabilities for shell access, file operations, or network exfiltration were found in the skill. Sanitization: There is no explicit sanitization of the input. Because the skill has no system-level capabilities to exploit, this input surface does not present a technical security risk.

linkedin-post