The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes the content of documentation files that may contain instructions.
Ingestion points: Reads content from documentation files (e.g., in docs/) and convention files like AGENTS.md (SKILL.md).
Boundary markers: Absent. There are no explicit delimiters or instructions to the agent to ignore potential instructions embedded within the documentation being translated.
Capability inventory: The skill uses Read, Write, Edit, and Glob tools to manipulate the local file system (SKILL.md).
Sanitization: None. The content is processed as raw text for translation.

translate-page