neurodivergent-founder

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill defines behavioral constraints for the agent to adopt a supportive persona. These instructions are legitimate for the skill's purpose and do not attempt to bypass core safety protocols.
  • [PROMPT_INJECTION]: Analyzed the surface for indirect prompt injection. 1. Ingestion points: User-provided tasks and outreach content (SKILL.md). 2. Boundary markers: None explicitly defined within the skill instructions. 3. Capability inventory: The skill prompts the agent to create or modify local files (CLAUDE.md) and generate task lists. 4. Sanitization: No specific sanitization or filtering logic is provided for external user content. This surface is standard for task-management utilities.
  • [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (ravila4/claude-adhd-skills) as a complementary resource. This is an informational link and not an automated download.
  • [NO_CODE]: No executable code, scripts, or automated package installations are included in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 11:47 AM
Security Audit — agent-trust-hub — neurodivergent-founder