campaign-planner
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of markdown files that serve as guides and templates for marketing professional services. No scripts, binaries, or automated network tools are included.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing user-supplied product and campaign details to generate text and code templates (HTML/React). This creates an inherent surface for indirect prompt injection where malicious data provided by the user could influence the agent's output.
- Ingestion points: User input for marketing goals, product USP, and campaign details as described in
SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the guides.
- Capability inventory: Textual planning and HTML/React code template generation.
- Sanitization: Relies on the core model's default safety filtering; no explicit validation or escaping is implemented in the skill instructions.
Audit Metadata