web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines from the Prisma Labs repository on GitHub to ensure the review process uses the latest standards.
- [INDIRECT_PROMPT_INJECTION]: The skill audits user-supplied source code, creating a surface where untrusted data could potentially contain instructions to influence the agent's behavior.
- Ingestion points: The skill reads files or patterns provided as arguments by the user.
- Boundary markers: No explicit delimiters or instructions are used to separate the guideline logic from the user-provided content.
- Capability inventory: The skill uses file system reading and network fetching (WebFetch).
- Sanitization: Content from the audited files is processed directly without explicit sanitization or filtering.
Audit Metadata