agency-data-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides templates for common data engineering tasks. No malicious behavior was detected.
- [PROMPT_INJECTION]: The instructions define a professional persona and operational rules without attempting to bypass safety filters, ignore previous instructions, or extract system prompts.
- [DATA_EXFILTRATION]: The skill does not access sensitive local file paths (such as SSH or AWS credentials) or perform unauthorized network requests. The Kafka and Spark examples use standard placeholder patterns.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found in the skill or the provided code snippets.
- [EXTERNAL_DOWNLOADS]: The skill does not instruct the agent to download unverified scripts or execute remote code from untrusted sources. All mentioned libraries (PySpark, Delta, dbt) are standard industry packages.
- [COMMAND_EXECUTION]: While the skill provides code snippets for data processing, it does not involve the execution of arbitrary or dangerous system commands.
Audit Metadata