The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted plaintext content from user-provided files which can contain malicious instructions targeting the agent's behavior during the conversion process.
Ingestion points: Documentation files provided via the #file parameter.
Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings to separate document content from agent instructions.
Capability inventory: The agent is instructed to perform file operations (copying) and deep text transformation, including regex-based updates.
Sanitization: No sanitization or escaping mechanisms are described for the content being processed.
[COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands for initial file setup.
Evidence: The usage examples demonstrate the agent executing cp and copy commands to create a .md version of a plaintext file before processing.
[EXTERNAL_DOWNLOADS]: The skill fetches formatting guidelines and technical documentation from well-known external sources to ensure markdown compatibility.
Evidence: Retrieves syntax guides from GitHub Docs, Markdown Guide, and Microsoft Learn via the #fetch tool.

convert-plaintext-to-md