The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local Python script at ~/.claude/skills/markdown-checker/scripts/check_markdown.py to perform document validation. This involves executing code within the agent's environment, which assumes the presence and integrity of the referenced script.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and optimize markdown content, including 'clippings' captured from external platforms like Twitter/X, which creates a potential vector for indirect prompt injection.
Ingestion points: The skill processes arbitrary markdown files and web clippings provided by the user.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the document content as data only and ignore any embedded instructions.
Capability inventory: The skill has the capability to execute shell commands (python3), read file contents, and perform extensive modifications to documents.
Sanitization: The instructions do not specify any sanitization or filtering to prevent the agent from obeying instructions hidden within the markdown being formatted.

markdown-formatter