campaign-planner
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, such as direct prompt injection, obfuscation, or remote code execution, were identified in the skill instructions, reference materials, or templates.
- [SAFE]: Data persistence is handled securely by writing campaign plans to a localized memory directory within the agent's environment, following established best practices for session management.
- [SAFE]: The skill references other internal marketing tools within its ecosystem using relative file paths, which is a standard and secure method for modular agent skill integration.
- [PROMPT_INJECTION]: The skill includes an ingestion surface for untrusted user data (e.g., brand descriptions and audience profiles) used to populate document templates. However, because this data is used only to generate static markdown content and does not interact with sensitive system tools or shell commands, the risk of indirect prompt injection is negligible.
Audit Metadata