marketing
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and summarize external product data (themes, plugins, and web products) to generate content.
- Ingestion points: Product details, feature lists, and marketplace descriptions (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the source product data.
- Capability inventory: The agent is authorized to create a multi-level directory structure and generate numerous markdown files (SKILL.md).
- Sanitization: The skill lacks explicit sanitization or validation steps for the incoming product data before it is formatted into marketing templates.
- [SAFE]: The skill follows security best practices for visual assets by explicitly instructing the agent to ensure no sensitive data is visible in product screenshots and to use real local development environments rather than unverified sources.
Audit Metadata