The Agent Skills Directory

[SAFE]: The instructions and metadata are consistent with the skill's purpose. No suspicious commands, network operations, or hardcoded credentials were found.
[PROMPT_INJECTION]: The skill processes data from the output of external tools, presenting a surface for indirect prompt injection (Category 8).
Ingestion points: Data returned by the list-initiatives tool into the initiatives parameter in SKILL.md.
Boundary markers: Uses the tool's JSON-array parameter structure as a delimiting boundary.
Capability inventory: Restricted to listing and summarizing initiatives via the One Horizon MCP tools.
Sanitization: No explicit validation or sanitization of input data is described in the instructions.

initiative-summary