The Agent Skills Directory

[SAFE]: The skill contains only natural language instructions to reformulate responses using Simplified Technical English (ASD-STE100). No executable code, system commands, or network operations are present.
[INDIRECT_PROMPT_INJECTION]: The skill references an external file (CONTEXT.md) for domain-specific terminology. 1. Ingestion points: Referenced in the body of SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No scripts or tool access available; disable-model-invocation is set to true. 4. Sanitization: Absent. This surface represents a low risk because the agent is restricted from calling external tools or other models.

wait-what