iris-development
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill demonstrates secure handling of API keys by recommending environment variables and secret managers rather than hardcoding credentials. It explicitly labels hardcoding as an incorrect practice.
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill references official Redis packages (redis-agent-memory and @redis-iris/agent-memory) available on standard registries. These are legitimate resources provided by the verified author.
- [PROMPT_INJECTION]: No patterns of prompt injection or instructions to bypass safety guidelines were found in the documentation or code snippets.
Audit Metadata