The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands including find, grep, and ls to identify project languages and frameworks during the detection phase.
[COMMAND_EXECUTION]: It invokes external verification tools and linters such as ruff, pydocstyle, npx eslint, and staticcheck to validate documentation standards.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) risks because it reads and processes local source code files to generate documentation.
Ingestion points: Code content from .py, .ts, .js, and .go files is read and passed to documentation agents in the verification and generation phases.
Boundary markers: The agent prompt templates in references/workflow.md do not utilize explicit delimiters or instructions to ignore embedded commands within the ingested code.
Capability inventory: The skill has access to the Edit tool for writing files, the Task tool for spawning sub-agents, and a shell environment for executing system commands.
Sanitization: There is no evidence of content sanitization or validation performed on the source code before it is interpreted by the language-specific agents.

ensure-docs