adhd-daily-planner
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted user input and processes external data.
- Ingestion points: User queries, task lists stored in files, and the OpenClaw memory system.
- Boundary markers: None identified in the prompt instructions to delimit user content from system instructions.
- Capability inventory: The skill can write to files (task lists, dopamine menus), store data in memory, and interact with other scheduling or note-taking skills.
- Sanitization: No specific sanitization or filtering of external content is described.
- [SAFE]: The skill's primary functions—daily planning, task breakdown, and emotional support—are implemented through standard instructional workflows. No evidence of malicious command execution, remote code downloads, or credential harvesting was found.
Audit Metadata