marketing-retention
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a high-level instructional framework for marketing strategies. It does not contain any executable code, shell commands, or network-enabled operations that could pose a security risk. All references to external sources (e.g., GitHub) and related skills are for informational purposes or process delegation within the agent's ecosystem. Legal compliance guidelines for Korean marketing regulations are included as a best practice.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to generate marketing campaign drafts and designs, which is a common surface for indirect prompt injection.
- Ingestion points: User-provided campaign requests and retention objectives (SKILL.md).
- Boundary markers: None explicitly defined in the instructional templates.
- Capability inventory: None; the skill does not have access to subprocesses, network writes, or file-writing tools.
- Sanitization: None; however, because the skill has no dangerous capabilities, the risk of injection causing harm is negligible.
Audit Metadata