The Agent Skills Directory

[SAFE]: The skill implements a standard task-handoff workflow designed to transfer state between agents with no context retention. The process uses a structured template to ensure all relevant information is captured without involving dangerous system calls or external dependencies.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it interpolates user-supplied arguments into a prompt intended for a secondary agent.
Ingestion points: User arguments are ingested via the $ARGUMENTS placeholder in SKILL.md.
Boundary markers: The briefing template uses clear Markdown headers (e.g., ## Task, ## Context) to structure information, though it lacks explicit instructions for the receiving agent to ignore potential commands within the context fields.
Capability inventory: The skill's primary capability is the automated creation of a new agent via the 'Paseo' orchestration tool using the generated briefing.
Sanitization: No sanitization is performed on user arguments; however, the structured nature of the handoff template serves as a natural delimiter.

paseo-handoff