goal-crafter
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level instructional guide for the AI agent to interact with users and format data. It does not perform any sensitive file operations, network requests, or command executions.
- [SAFE]: Instructions focus on 'standalone mode' (user interview) and 'compiled-handoff mode' (processing data from other skills), which are standard workflow patterns for multi-agent systems.
- [SAFE]: No obfuscation, data exfiltration, or malicious prompt injection patterns were detected. The skill promotes security best practices by encouraging users to define constraints (e.g., 'don't touch certain files', 'read-only mode').
- [SAFE]: External references in documentation (GitHub URLs) point to open-source project structures and development workflows common in the AI agent community.
Audit Metadata