The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/md-to-eml.cjs executes the external pandoc binary using a shared tool-runner.cjs utility to perform Markdown-to-HTML conversion.- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external Markdown files which may contain untrusted data. If an agent processes a malicious Markdown file, it could be influenced by embedded instructions or exploit the skill's file-handling capabilities.
Ingestion points: The sourcePath file content is read and processed in scripts/md-to-eml.cjs.
Boundary markers: The script does not implement explicit boundary markers or instructions for the agent to ignore embedded commands within the Markdown body.
Capability inventory: The skill performs file reads (fs.readFileSync for images), file writes (fs.writeFileSync for the output .eml and debug files), and external command execution (runTool for pandoc).
Sanitization: Image paths are resolved and validated against a specific list of allowed extensions (.png, .jpg, .jpeg, .gif, .webp) before reading.

md-to-eml