web-design-guidelines
Warn
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: MEDIUMMETADATA_POISONINGEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's metadata claims the author is "vercel," whereas the provided skill context identifies the author as "ma1orek." This is a deceptive claim regarding the skill's provenance.
- [EXTERNAL_DOWNLOADS]: The skill fetches configuration and guidelines from the official Vercel Labs repository on GitHub. This is an expected operation from a well-known service provider.
- [INDIRECT_PROMPT_INJECTION]: The skill dynamically ingests instructions from an external URL, which establishes an indirect prompt injection surface if the external content is compromised.
- Ingestion points: Fetches guidelines from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md(SKILL.md). - Boundary markers: No delimiters or explicit instructions to ignore embedded commands in the external data are present.
- Capability inventory: The skill utilizes
WebFetchto access the network and provides functionality to read local project files. - Sanitization: No sanitization, validation, or schema enforcement of the retrieved external content is described.
Audit Metadata