strategic-compact

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation instructs the user to modify their environment configuration (~/.claude/settings.json) to trigger a local script (suggest-compact.sh) during tool execution. This is the intended functional mechanism of the skill.
  • [DATA_EXPOSURE]: The provided tracking script uses a local temporary file (/tmp/claude-tool-count-*) to store a numeric counter associated with the current session. This file does not contain sensitive user data or system information.
  • [INDIRECT_PROMPT_INJECTION]: The script generates reminders that are fed back into the agent's context via standard error. These messages are static, non-malicious prompts recommending the use of the /compact command based on usage volume, posing no security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:17 AM