data-quality-checker
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill identifies a data ingestion surface through its purpose of assisting with data pipeline tasks. 1. Ingestion points: User requests and metadata regarding ETL and data transformation workflows. 2. Boundary markers: Not specified in the provided markdown. 3. Capability inventory: Read, Write, Edit, Bash, and Grep tools are allowed for the agent. 4. Sanitization: No sanitization logic or delimiters are defined in the static configuration. Despite the surface, no active exploitation or malicious patterns were found.
- Metadata Poisoning (SAFE): The skill metadata including name, description, and author information is consistent with its stated purpose and does not contain hidden prompt injection markers or deceptive content.
Audit Metadata