strategic-compact
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill operates entirely within the local environment using standard shell commands.
- [COMMAND_EXECUTION]: The skill implements a bash script (
suggest-compact.sh) designed to run as a local PreToolUse hook. This script performs basic file I/O on a temporary counter file (/tmp/claude-tool-count-$$) and outputs status messages to standard error.
Audit Metadata