i-have-adhd

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions designed to modify the agent's persona and response formatting (e.g., leading with actions, using numbered lists, and providing time estimates).
  • [NO_CODE]: The skill does not include any scripts, executable code, or platform-level tool calls. Example commands provided in the text are illustrative examples for the agent's output style.
  • [PROMPT_INJECTION]: While the skill contains strong instructions to maintain persona persistence ("These rules apply to every response for the rest of the session"), these are standard behavioral constraints for a formatting skill and do not attempt to bypass safety filters or extract system prompts.
  • [DATA_EXFILTRATION]: There are no mechanisms for file access or network communication. The skill's configuration specifically disables model invocation of tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 07:26 PM
Security Audit — agent-trust-hub — i-have-adhd