prompt-proximity-architecture
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a logical framework for organizing and designing prompt coverage across different proximity bands and journey states. No malicious instructions, obfuscation, or safety bypasses were detected.
- [DATA_EXPOSURE]: The skill references local data files such as icp_hypotheses.json and buyer_jobs.json, and internal project documentation at ../build-ai-visibility-panel/references/artifact-contracts.md. These interactions are consistent with its stated purpose of architecting prompts based on project inputs and do not target sensitive system files or credentials.
- [REMOTE_CODE_EXECUTION]: The skill does not include any instructions for downloading external payloads, installing unverified dependencies, or executing remote scripts.
Audit Metadata