skills/b-open-io/prompts/hammertime/Gen Agent Trust Hub

hammertime

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'scripts/create-timer.py', a Python script used to manage timer-based rules and perform atomic writes to the rules configuration file at '~/.claude/hammertime/rules.json'.
  • [SAFE]: The 'Phase 2' verification process involves sending agent responses to a well-known AI service (Anthropic's Haiku model) for scoring, which is a standard pattern for providing the described guardrail functionality.
  • [SAFE]: The skill maintains its configuration and state within a dedicated local directory and does not attempt to access sensitive system files or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:08 PM