The Agent Skills Directory

[SAFE]: The skill consists of purely instructional content, tables, and workflow templates designed to guide an AI agent in translation tasks.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read a local file named contextus.md to gather project context.
Ingestion points: Reads contextus.md from the project root.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: The skill itself has no scripts, network access, or file-writing capabilities.
Sanitization: None specified for the ingested content.
Analysis: While the skill ingests external data, it lacks the necessary capabilities to perform data exfiltration or system modification, making the surface area for exploitation minimal.
[NO_CODE]: There are no scripts, binaries, or configuration files provided with the skill that could perform actions on the host system.

translation