The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes documentation and terminology files which could serve as a vector for indirect prompt injection if they contain malicious instructions.
Ingestion points: Accesses README.md, translation-rules.md, terminology.md, and i18n-glossary.json within the repository.
Boundary markers: The instructions do not specify delimiters to isolate the content being translated from the agent's instructions.
Capability inventory: The agent is authorized to run pnpm commands for documentation checks.
Sanitization: No specific sanitization logic is defined for the ingested text.
[COMMAND_EXECUTION]: The skill utilizes pnpm to run local documentation validation scripts.
Evidence: Execution of pnpm docs:check-pairing and pnpm docs:check is required to verify the integrity of the translated pairs.

translate-docs