strategic-compact

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide educational content and a simple utility for managing large context windows. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
  • [COMMAND_EXECUTION]: The skill includes a bash script (suggest-compact.sh) designed to run as a hook. It increments a session-specific counter in a temporary file (/tmp/claude-tool-count-*) and outputs suggestions to standard error once thresholds are met. This behavior is benign and aligns with the stated purpose of the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation references an external resource on X (Twitter) for context optimization techniques. This is a link to a well-known social media platform for informational purposes and does not involve automated downloads or execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 07:57 PM