The Agent Skills Directory

[SAFE]: The skill is entirely instructional and serves as a diagnostic tool for organizational alignment. It does not include any commands for remote code execution, persistence, or data exfiltration.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to process external organizational data.
Ingestion points: Data provided by the user describing organizational strategy, structure, and systems.
Boundary markers: Not explicitly defined in the prompt instructions to separate data from instructions.
Capability inventory: The skill uses Read, Write, Edit, and Agent tools (defined in SKILL.md) which allow it to interact with the file system and other agents.
Sanitization: None detected for the ingested data.

mckinsey-7s