The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/check_markdown.py to automate the detection of markdown syntax and style issues. This command execution is a core feature of the tool's linting capabilities.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes the content of markdown files, which presents a surface for indirect prompt injection if the files contain instructions designed to manipulate the agent.
Ingestion points: The load_file function in scripts/check_markdown.py reads the entire content of targeted markdown files; the Manual Check Flow in SKILL.md instructs the agent to use the Read tool on user-specified files.
Boundary markers: The skill does not define specific delimiters or provide instructions to the agent to disregard potentially malicious instructions embedded within the markdown content.
Capability inventory: The skill instructions in SKILL.md suggest the agent use Read and Edit tools to process and fix identified issues in the files.
Sanitization: No sanitization or filtering is applied to the markdown content before it is read or analyzed by the script or the agent.

markdown-checker