web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from a remote repository at https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. This is a routine operation to retrieve configuration content from an established organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and executes instructions from an external URL, which could be modified to include malicious prompts.
  • Ingestion points: The skill fetches instructions from an external Markdown file (command.md) and processes user-provided UI code files as input.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the fetched content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes WebFetch to retrieve remote content and has the capability to read local files provided by the user.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content fetched from the remote guidelines source.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — web-design-guidelines