honest-agent
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate configuration tasks for AI development tools.
- [COMMAND_EXECUTION]: The skill instructs the agent to locate, read, and modify local configuration files (e.g.,
.claude/CLAUDE.md,.cursorrules,~/.continue/config.json). This is the core intended functionality. The instructions repeatedly emphasize a defensive 'APPEND ONLY' strategy to prevent accidental data loss or the overwriting of existing user instructions. - [EXTERNAL_DOWNLOADS]: The skill references documentation and official resources from well-known technology companies (Anthropic, GitHub, Cursor, Codeium). No external code or scripts are downloaded or executed by the skill.
Audit Metadata