The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted source text for translation and localization into various Chinese variants. Ingestion points: Untrusted source text for translation and localization. Boundary markers: There are no explicit delimiters or specific instructions for the agent to distinguish between the skill's instructions and potentially malicious commands embedded in the source text data. Capability inventory: The skill does not request or use any high-risk tools, network access, file system operations, or shell execution. Sanitization: No sanitization, validation, or escaping of the user-provided content is implemented in the logic.

localize-zh