The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx to execute commands for scraping, refreshing, and removing documentation from a local index.
[EXTERNAL_DOWNLOADS]: The skill fetches the @arabold/docs-mcp-server package from the NPM registry at runtime. This package is maintained by the skill author.
[DATA_EXPOSURE]: The scrape command allows the agent to read and index local files using the file:// protocol. This is a documented feature for indexing local documentation.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and local files to build a documentation index. This creates an attack surface for indirect prompt injection if the source content contains malicious instructions.
Ingestion points: The scrape command accepts arbitrary URLs and local file paths (SKILL.md).
Boundary markers: The instructions do not define delimiters or warnings to ignore instructions embedded within the scraped content.
Capability inventory: The skill uses npx for command execution and has the ability to read from the network and local file system (SKILL.md).
Sanitization: No sanitization or validation of the scraped content is specified in the prompt instructions.

docs-manage