The Agent Skills Directory

[SAFE]: The skill serves as an organizational directory, mapping job descriptions to specific internal tools. It does not perform network operations, file modifications, or system-level commands.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by accepting user-supplied task descriptions to determine routing. * Ingestion points: User input enters via the argument-hint defined in SKILL.md. * Boundary markers: The instructions do not define delimiters to isolate user input from the routing logic. * Capability inventory: The skill is limited to calling the Skill tool for redirection. * Sanitization: No specific input sanitization is implemented within the skill logic.

map