alterlab-nmc-digital-campaign
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions are focused entirely on digital campaign strategy and content creation. No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were found.- [DATA_EXFILTRATION]: While the skill performs web searches and reads project files for context, these operations are restricted to legitimate research purposes aligned with the campaign planning role. No suspicious exfiltration of sensitive files or credentials was detected.- [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, external package installations, or remote code download patterns. It provides recommendations for third-party platforms (e.g., Change.org, Mailchimp) to be used by the human operator.- [PROMPT_INJECTION]: The skill contains task-specific constraints and ethical guidelines (e.g., center community voices, verify statistics) that reinforce rather than bypass safety protocols. No jailbreak attempts or behavioral overrides were identified.
Audit Metadata