The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze external source code files provided at the <source-path>. This data is untrusted and could contain maliciously crafted JSDoc comments or string literals intended to override the agent's instructions during the parsing and documentation generation process.
Ingestion points: Reads source code from the user-provided <source-path> as described in SKILL.md.
Boundary markers: None identified; the skill does not specify delimiters or instructions to ignore embedded prompts within the source code.
Capability inventory: The skill has access to Bash(npx *), Write, Read, Grep, and the mcp__plugin_ruflo-core_ruflo__hooks_worker-dispatch tool.
Sanitization: None identified; the skill extracts and processes content directly from JSDoc annotations.
[COMMAND_EXECUTION]: The skill configuration allows for the execution of npx commands through the Bash tool. While this is a common developer workflow for running documentation tools (like JSDoc or OpenAPI generators), npx inherently involves fetching and executing packages from the npm registry, which presents a command execution and external dependency surface.

api-docs