mcp-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to override system behavior, bypass safety filters, or extract system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations detected.
- [Unverifiable Dependencies] (SAFE): References standard packages (mcp-use, zod). No remote script execution or untrusted package installations.
- [Indirect Prompt Injection] (LOW): The skill provides templates for creating tools and prompts that ingest untrusted data. 1. Ingestion points: Tool parameters and prompt parameters in SKILL.md code snippets. 2. Boundary markers: Absent in the templates. 3. Capability inventory: Generated code uses text/object responses; no dangerous system capabilities like shell execution or file-writing are provided in templates. 4. Sanitization: Absent in the code snippets.
Audit Metadata