The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several pnpm scripts (such as docs:check, lint, and docs:affected) and git commands for repository maintenance and validation. These commands are typical for a development workflow and are used for their intended purpose of checking documentation and code health.
[INDIRECT_PROMPT_INJECTION]: The skill reads data from repository files which could theoretically contain malicious instructions.
Ingestion points: The agent is instructed to read AGENTS.md, module READMEs, and files within the docs/ directory.
Boundary markers: The instructions do not specify the use of delimiters or ignore-behavior warnings when reading these files.
Capability inventory: The agent can execute pnpm and git commands as defined in the governance process.
Sanitization: There are no explicit sanitization steps mentioned for the processed documentation content. Although this represents a vulnerability surface, the risk is localized to the repository's own documentation files.

docs-governance