The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external content in the form of translation drafts and glossaries, creating a potential surface for indirect instructions to influence agent behavior.
Ingestion points: The skill ingests a translating-core draft, project context, glossaries, and style guides (found in SKILL.md).
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested translation drafts.
Capability inventory: The skill interacts with other agent skills (reviewing-translations, translating-products) and is authorized to perform targeted market research via an orchestrator.
Sanitization: The instructions do not specify any sanitization or validation steps for the input text before refinement.

translating-portuguese