The Agent Skills Directory

[SAFE]: The skill instructions define a clear, task-oriented persona for technical writing. No evidence of prompt injection, data exfiltration, or malicious commands was found. The skill operates within a restricted scope, explicitly forbidding external network requests unless provided by the user.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest markdown files for context.
Ingestion points: Markdown files provided by the user (SKILL.md).
Boundary markers: None explicitly defined to separate user context from system instructions.
Capability inventory: The skill is limited to generating text/markdown content. It lacks capabilities for subprocess execution, file system modification, or network operations.
Sanitization: No explicit sanitization or filtering of input data is mentioned. However, due to the lack of sensitive capabilities, the overall risk is negligible.

documentation-writer