web-design-guidelines
Warn
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill metadata claims the author is 'vercel', which contradicts the actual publisher identity 'shuffleo'. This deceptive naming can lead users to misinterpret the skill's origin and trust level.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md' at runtime to define its review criteria.
- [PROMPT_INJECTION]: The skill is architected to ingest and execute instructions from a remote markdown file, creating a vulnerability surface for indirect prompt injection. \n
- Ingestion points: The skill retrieves rules and formatting instructions from a remote GitHub URL before each review. \n
- Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the fetched guidelines. \n
- Capability inventory: The agent has the ability to fetch external web content and access local project files. \n
- Sanitization: The skill does not perform validation or sanitization on the fetched guidelines before using them to direct the agent's behavior.
Audit Metadata