The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions.
[PROMPT_INJECTION]: The skill processes external documentation files which creates a surface for indirect prompt injection. However, its purpose is limited to text organization and creation of local documentation.
Ingestion points: Ingests user-provided markdown files (e.g., AGENTS.md).
Boundary markers: Absent; there are no specific delimiters to separate user content from agent instructions.
Capability inventory: Capability to create and write files as part of the refactoring process.
Sanitization: No sanitization is performed on the ingested text.
[COMMAND_EXECUTION]: Examples of build and test commands (like pnpm build) are included in templates for documentation purposes only and are not intended for shell execution.
[DATA_EXFILTRATION]: No attempts to access sensitive system files or establish network connections were found.

agent-md-refactor