marketing-campaign-planner

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied campaign requirements (such as target audience, budget, and channel information) to generate strategic documents. This creates a standard ingestion surface for indirect prompt injection.
  • Ingestion points: User-provided campaign prompts and target data in SKILL.md.
  • Boundary markers: The skill does not explicitly define delimiters for user input, relying on the agent's internal handling.
  • Capability inventory: The skill has no direct file-write, network, or subprocess capabilities; it purely generates text based on templates.
  • Sanitization: The skill includes a mandatory post-processing chain (ai-slop-reviewer and korean-humanize) followed by a final human review step to verify output quality and safety.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:23 PM