campaign-planning
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected in the instructions or evaluation files. The skill operates as a purely instructional template for planning marketing campaigns.
- [NO_CODE]: The skill does not contain any scripts, binary files, or external package dependencies. It relies entirely on natural language processing within the agent's internal environment.
- [PROMPT_INJECTION]: The instructions do not contain any bypass attempts, role-play injections, or commands to ignore previous safety guidelines. The constraints in the "NEVER DO THESE" section are benign marketing best practices.
- [DATA_EXFILTRATION]: There are no commands or network patterns (like curl or wget) that would allow for data to be sent to external servers. The skill does not request access to sensitive file paths or credentials.
Audit Metadata