Skills
Navigate
skills/hainrixz/claude-webkit/web-design-guidelines/Gen Agent Trust Hub

web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from Vercel Labs' official GitHub repository.
  • [METADATA_POISONING]: The author field in the skill metadata is set to vercel, which does not match the provided author identifier hainrixz. This discrepancy can be misleading regarding the skill's origin.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content and local code files, making it a potential target for instructions hidden within data.
  • Ingestion points: Fetches command.md from a remote URL and reads local files provided by the user.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present for the ingested content.
  • Capability inventory: The skill uses WebFetch and file read operations to audit code.
  • Sanitization: No sanitization or validation of the input content is described before the audit process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:16 PM