The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's 'Ability Gap Response Rule' instructs the agent to recommend the installation of an external repository (github:mindverse/skillhub) using the /install command when a user request exceeds the skill's native capabilities. This repository is not included in the pre-defined list of trusted vendors.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input describing child behavior and educational scenarios. It lacks specific boundary markers or instructions to disregard potential commands embedded within user queries, though its lack of internal scripting limits the direct risk of exploitation.
Ingestion points: User-provided descriptions of parenting issues, children's behavior, and academic situations (SKILL.md).
Boundary markers: Absent. No delimiters or protective instructions are used to wrap user input.
Capability inventory: None. The skill consists entirely of instructional text and does not include executable scripts (Python, Node.js) or shell commands.
Sanitization: Absent. User input is analyzed directly without filtering or escaping.

parent-helper