The Agent Skills Directory

[SAFE]: The skill is an administrative utility for managing workspace squads. It appropriately restricts its operations to the authorized multica CLI tool as specified in the skill configuration.
[PROMPT_INJECTION]: The skill interacts with issue comments and descriptions, which constitutes a potential surface for indirect prompt injection. This risk is inherent to the skill's primary function of issue management and coordination.
Ingestion points: The skill ingests untrusted data from issue descriptions and comments using multica issue get and multica issue comment list (found in SKILL.md).
Boundary markers: The instructions do not explicitly define boundary markers or 'ignore embedded instructions' warnings for the data being processed.
Capability inventory: The skill possesses the ability to mutate workspace state via multica squad management commands and multica issue update (found in SKILL.md).
Sanitization: No explicit sanitization, validation, or escaping of ingested external content is described in the provided skill files.

multica-squads