deliverability-checker
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions designed to bypass agent constraints or override system behavior were detected.
- [Data Exposure & Exfiltration] (SAFE): There are no patterns suggesting the exfiltration of sensitive data or hardcoded credentials. Network activity is limited to standard DNS lookups.
- [Unverifiable Dependencies] (SAFE): The required packages,
dnspythonandclick, are widely used and trustworthy dependencies from the official Python Package Index. - [Indirect Prompt Injection] (LOW): The skill processes external DNS data which is theoretically attacker-controllable. However, this is a known risk for any auditing tool and no specific exploits were found. Evidence Chain: 1. Ingestion points: DNS record strings retrieved via scripts/main.py. 2. Boundary markers: Not specified in instructions. 3. Capability inventory: Command execution (python script) and diagnostic reporting. 4. Sanitization: Not explicitly implemented in provided files.
- [Remote Code Execution] (SAFE): No remote scripts or unverified binary downloads are performed; the skill executes a local Python script referenced in the documentation.
Audit Metadata