ai-agents-architect
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides architectural guidance and best practices for building AI agents. It consists solely of documentation and metadata; it does not include any executable code, scripts, or dangerous tool definitions.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided agent designs and code snippets, which could contain embedded malicious instructions. However, because the skill lacks active capabilities (such as network access, file system writes, or shell execution), this ingestion surface does not pose a functional security risk. Ingestion points: User-supplied requests and code snippets processed according to SKILL.md. Boundary markers: Instructions in SKILL.md mandate prioritizing the provided reference files as the source of truth. Capability inventory: None. No tools or external interactions are defined. Sanitization: None.
Audit Metadata