rules-distill

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell scripts (scan-skills.sh, scan-rules.sh) to inventory metadata and headings from markdown files in the user's home directory. These scripts perform read-only operations using standard tools (find, grep, awk, jq) and do not modify the file system or execute remote code.
  • [AUTONOMY_REVIEW]: The instructions explicitly state that the agent must never modify rules automatically and always require user approval before applying any suggested changes.
  • [DATA_EXPOSURE]: The skill reads .md files in ~/.claude/rules and ~/.claude/skills. While these contain system/agent instructions, the analysis is performed locally by the agent and summarized for the user. No network exfiltration or transmission of this data is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — rules-distill