mcp-builder
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill outlines a structured development framework for building and orchestrating MCP integrations. The instructions focus on cognitive integrity, version pinning, and surgical code changes.
- [DATA_EXFILTRATION]: The skill promotes security hygiene by instructing the agent to redact secrets and PII before sharing context with subagents, acting as a safeguard against data leakage.
- [INDIRECT_PROMPT_INJECTION]: The instructions explicitly identify external data and web content as hostile sources, directing the agent to maintain safety boundaries when processing untrusted inputs.
Audit Metadata