context-layer-architect
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate tool for context engineering and documentation management, focused on improving AI agent interactions with complex codebases.
- [SAFE]: It utilizes platform-provided tools such as Task for parallel exploration and Write/Edit for file system modifications in a manner consistent with its stated goals.
- [SAFE]: No obfuscation, data exfiltration, or hardcoded credentials were detected in the skill instructions or associated reference materials.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and analyze potentially untrusted codebase files. Ingestion points: Exploration agents (Agent 1-4) reading file content. Boundary markers: Absent in the instructions for data processing. Capability inventory: Access to Task, Write, Edit, and AskUserQuestion tools. Sanitization: No explicit content sanitization or instruction filtering is implemented for ingested data.
Audit Metadata