mcp-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill is a documentation-only resource. No executable code or suspicious patterns were found.
  • PROMPT_INJECTION (SAFE): No attempts to override agent behavior or bypass safety filters were detected.
  • EXTERNAL_DOWNLOADS (SAFE): No remote scripts or packages are downloaded or executed.
  • DATA_EXFILTRATION (SAFE): No sensitive data access or external network calls are present.
  • INDIRECT_PROMPT_INJECTION (SAFE): While the skill defines principles for tool design, it does not ingest untrusted data in a way that creates a vulnerability surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:42 PM