The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/md2idx-run.sh script uses npx -y md2idx to download and execute the md2idx package from the public npm registry if it is not already available locally or in the environment path.
[COMMAND_EXECUTION]: The skill requires permission to run a bundled shell script, scripts/md2idx-run.sh, which executes system commands like wc, jq, and the md2idx tool to process Markdown files and extract content.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and processes external Markdown files that could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Data is ingested from external Markdown files located on the local file system through the md2idx tool or fallback methods using grep and the Read tool.
Boundary markers: The skill does not implement specific boundary markers or instructions to the agent to ignore embedded commands within the retrieved Markdown sections.
Capability inventory: The agent has access to file system read operations and shell execution via the provided wrapper script.
Sanitization: No validation or sanitization of the file content is performed prior to presenting it to the agent's context.

md2idx-read