adhd-advisor

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Extensive analysis of the skill's logic and metadata revealed no malicious intent, hidden commands, or security vulnerabilities. The skill operates entirely through structured prompting.
  • [PROMPT_INJECTION]: The skill is free of prompt injection triggers. It explicitly defines its scope to personal tasks and includes defensive instructions to the agent to treat user-provided task descriptions as potentially malicious, requiring sanitization and path validation.
  • [COMMAND_EXECUTION]: There is no evidence of automated command execution. While technical examples suggest the use of tools like grep, these are intended as manual or logic-based steps within the agent's interpreted environment, rather than direct system-level execution patterns.
  • [EXTERNAL_DOWNLOADS]: The skill does not attempt to download or execute code from external sources. All referenced files (e.g., @references/adhd-task-strategies.md) are internal to the skill's own package.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:32 AM