skills/agentara/skills/super-daddy/Gen Agent Trust Hub

super-daddy

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill manages a local directory at ~/.super_daddy/ to store child profiles, case records, and parenting plans. This storage is used for persistence and session continuity, with instructions included to avoid storing this data in shared or repository folders to protect user privacy.
  • [COMMAND_EXECUTION]: The skill utilizes the imagegen tool to generate visual parenting plans for non-urgent caregiver actions. These tool calls are gated by profile completeness and visit clarification checks to ensure the output is grounded in confirmed facts.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to build a child profile in parenting.md, which is subsequently used to influence planning and tool invocation (imagegen). It manages this surface by enforcing structured workflow gates (Stage 1-4) and requiring explicit verification of facts before they are used in automated tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:17 AM
Security Audit — agent-trust-hub — super-daddy