contact-verification
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as prompt injection, obfuscation, or unauthorized data exfiltration, were identified. The skill instructions and metadata are consistent with its primary purpose of managing email deliverability.
- [COMMAND_EXECUTION]: The skill includes scripts/check-output.py, which is used to verify the presence of specific keywords in the agent's output. The script uses standard libraries (sys, pathlib) and does not perform any risky operations like network access or arbitrary command execution.
- [DATA_EXFILTRATION]: The skill manages contact data and recommends the use of email verification services. These actions are transparently documented as part of the intended workflow and do not represent a security risk.
Audit Metadata