ad-creative-design
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes brand guidelines from an external local file which may contain instructions that could influence the agent's behavior during the creative process.
- Ingestion points: The skill reads brand colors, fonts, and styles from
.agents/design-context.mdin Step 1. - Boundary markers: None identified; the skill does not use delimiters to isolate the content of the design context file.
- Capability inventory: The skill generates HTML5, CSS, and JavaScript code as its primary output.
- Sanitization: No sanitization or validation of the input file content is mentioned.
- [DYNAMIC_EXECUTION]: The skill generates functional code, including JavaScript and CSS animations, to produce production-ready HTML5 ads.
- Evidence: Step 8 includes a JavaScript snippet for implementing a
clickTag(var clickTag = "https://example.com";), and Step 9 provides templates for CSS@keyframesanimations.
Audit Metadata