web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the latest web interface guidelines from Vercel Labs' official GitHub repository (vercel-labs/web-interface-guidelines). This is a legitimate source for design compliance rules.
  • [METADATA_POISONING]: There is a discrepancy between the metadata author field ('vercel') and the provided author context ('akillness'). This may indicate the skill was ported or forked from an original source, though it does not affect the code's operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests and obeys instructions from an external file to perform code reviews.
  • Ingestion points: SKILL.md (fetches content from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md)
  • Boundary markers: None specified; the agent is instructed to "Apply all rules from the fetched guidelines".
  • Capability inventory: File read operations for local UI code, network fetching of guidelines via WebFetch.
  • Sanitization: No explicit sanitization or validation of the fetched Markdown content is performed before it is applied to the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 08:42 AM