ai-design-dot-md
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and ingest data from untrusted source files within a project, such as
package.json,tailwind.config.js, CSS/SCSS files, and component directories, to extract design tokens. This creates an attack surface where an attacker could embed malicious instructions within these source files (e.g., in comments or string literals) to influence the agent's behavior. - Ingestion points: The skill explicitly scans
package.json, framework configurations, global CSS/SCSS files, and component files during Phase 2 (Extract mode). - Boundary markers: No specific boundary markers, delimiters, or "ignore embedded instructions" warnings are implemented for the data read from project files.
- Capability inventory: The skill possesses the capability to read project files and write the
DESIGN.mdfile to the project root or a sub-directory. - Sanitization: There is no evidence of sanitization, escaping, or validation of the text content extracted from the source files before it is processed or used to generate the output specification.
Audit Metadata