The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for translation and localization, creating a potential surface for indirect prompt injection where hidden instructions in the source text could attempt to influence the agent's behavior.
Ingestion points: External text content provided by the user for translation and localization as described in SKILL.md.
Boundary markers: The instructions do not specify the use of clear delimiters or boundary markers to isolate the text being translated from the agent's system instructions.
Capability inventory: The skill uses the strale_translate tool via the sandbase_call_tool interface to perform translation tasks.
Sanitization: There are no explicit instructions for the agent to sanitize, filter, or escape the input text before processing it.

content-translator