connector-manager
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements management functions for data connectors and handles sensitive credentials using best-practice instructions. It explicitly directs the agent to mask API keys and avoid echoing secrets in user-facing responses to prevent accidental data exposure.- [PROMPT_INJECTION]: The skill processes user-supplied API configurations and keys as ingestion points in SKILL.md. It employs logical boundary markers via safety instructions to mask secrets. Its capability inventory includes network requests via dataBridgePull and secret storage via dataBridgeSetCredentials. Sanitization is enforced through mandatory instruction-based masking of sensitive values.
Audit Metadata