web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill retrieves a remote file from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md' to determine its rules.
- Evidence: The [TRUST-SCOPE-RULE] applies as 'vercel-labs' is a trusted GitHub organization, downgrading this finding to LOW/INFO.
- PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection because it executes logic defined in external data.
- Ingestion points: Remote content fetched from 'command.md' via WebFetch.
- Boundary markers: None; the agent is instructed to 'Apply all rules from the fetched guidelines' without validation.
- Capability inventory: Reading local project files provided by the user.
- Sanitization: Absent; the skill blindly adopts the instruction set and output format from the remote source.
Audit Metadata