buildbetter-mcp-research
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a comprehensive and security-conscious research workflow. It explicitly enforces a read-only approach by instructing the agent not to call tools annotated as mutating and to hand off to mutation workflows only after user approval. It also prioritizes specialized domain tools over raw GraphQL queries (
run-query), which follows the principle of least privilege and reduces the risk of accidental or malicious data manipulation. The skill maintains transparency by requiring the agent to output the specific scope, filters, and identifiers used in its research, allowing for human verification of the findings.
Audit Metadata