design-taste-frontend
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and verify dependencies within the project's
package.jsonfile. This ingestion of untrusted external data, combined with the capability to generate code and terminal installation commands, creates a surface for indirect prompt injection. Malicious instructions could potentially be embedded in dependency metadata to influence the agent's behavior during code generation.\n - Ingestion points:
package.json(referenced inSKILL.mdandreferences/design-rules.md).\n - Boundary markers: Absent; the skill does not provide delimiters or instructions for the agent to ignore potentially malicious content within the file.\n
- Capability inventory: Generates React/Next.js components and provides terminal installation commands (npm/yarn/pnpm).\n
- Sanitization: Absent; no explicit validation or filtering of the file's content is described.
Audit Metadata