confluent-skill-creator
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strong security guardrails for handling sensitive information. It explicitly prohibits reading, displaying, or logging the contents of
.envorcredentials.yamlfiles, instructing the agent to only verify the existence of environment variables rather than their values. - [SAFE]: The skill mandates the use of synthetic data (e.g., example.com domains, 555-01xx phone numbers) for all eval prompts, fixtures, and sample records, reducing the risk of PII exposure.
- [COMMAND_EXECUTION]: The skill uses several Python scripts (
scripts/check_compute_pool.py,scripts/produce_data.py, etc.) to interact with Confluent infrastructure. These interactions are performed using official client libraries (confluent-kafka) and standard APIs, following documented best practices. - [EXTERNAL_DOWNLOADS]: The skill references official Confluent documentation (docs.confluent.io) and well-known repositories (github.com/confluentinc, github.com/anthropics). These references are used for documentation and schema validation purposes and are considered safe under the trust-scope rules.
Audit Metadata