The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process the contents of markdown files within a repository, which represents a potential surface for indirect prompt injection if those files contain malicious instructions disguised as documentation.\n- Ingestion points: The skill reads from skills/*/SKILL.md and README.md files.\n- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the files being processed.\n- Capability inventory: The agent is tasked with file system read and write operations to manage translations.\n- Sanitization: No sanitization or filtering of the source documentation content is performed before translation.

docs-i18n-zh