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
.mdfiles in~/.claude/rulesand~/.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