adhd-task-management-skill

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill follows its stated purpose of managing task workflows for ADHD support.\n- [DATA_EXFILTRATION]: The skill logs task metadata (description, duration, domain, and state) to a Supabase 'activities' table. This is a core feature for trend analysis and uses a well-known service provider.\n- [PROMPT_INJECTION]: The skill processes user-supplied task descriptions which creates a surface for indirect prompt injection.\n
  • Ingestion points: User-provided task names and progress updates.\n
  • Boundary markers: The skill uses internal JSON objects to structure data before processing or logging.\n
  • Capability inventory: Capabilities are limited to conversational interaction and database insertion; no shell access or dangerous functions were found.\n
  • Sanitization: No explicit sanitization of input strings is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:32 AM