rule-creator
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely documentation-oriented. All referenced files are markdown documents providing guidance on project configuration and best practices. There are no executable scripts, binaries, or network operations included in the skill.- [DATA_EXFILTRATION]: The skill references local configuration paths such as ~/.claude/CLAUDE.md and .claude/rules/. These are standard locations for the Claude Code platform's configuration and are mentioned solely for instructional purposes; no logic for unauthorized data access or exfiltration exists.- [PROMPT_INJECTION]: The skill provides advice on how to write effective instructions for the agent but does not contain any patterns aimed at bypassing safety guardrails, overriding system constraints, or performing unauthorized actions.
Audit Metadata