chainlink-data-streams-skill

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official vendor documentation and open-source SDK repositories.
  • It directs the agent to fetch documentation from official sources and GitHub repositories under the smartcontractkit organization to ensure information freshness.
  • It recommends the @upstash/context7-mcp server for context retrieval, which is a well-known service for providing LLM context.
  • [COMMAND_EXECUTION]: The skill instructions allow use of the Bash tool for standard local development tasks.
  • The agent is guided to use the tool for generating code, performing local tests with Foundry and Hardhat, and managing dependencies.
  • These activities are regulated by an approval protocol and a second confirmation rule to prevent unauthorized actions.
  • [SAFE]: The skill provides robust safety guardrails and privacy protections.
  • It explicitly instructs the agent to avoid exposing sensitive data like API secrets, private keys, or billing information.
  • It restricts on-chain actions to testnets only, refusing all mainnet state changes while allowing read-only access for documentation purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 05:24 PM
Security Audit — agent-trust-hub — chainlink-data-streams-skill