web-design-guidelines
Warn
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: MEDIUMMETADATA_POISONINGEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's metadata identifies the author as 'vercel', but the actual author is 'lucasduarteinacio'. This discrepancy is deceptive and could lead users to misjudge the trust level and safety of the skill.
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch design guidelines from the official Vercel Labs repository on GitHub. While the target domain is a well-known service, the skill uses the fetched content as dynamic instructions to guide its review process.
- [INDIRECT_PROMPT_INJECTION]: The skill reviews user-provided files, which serves as an ingestion point for potentially malicious instructions hidden in the analyzed data.
- Ingestion points: User-specified files or file patterns provided as arguments in SKILL.md.
- Boundary markers: None are defined in the instructions to separate the untrusted file content from the agent's core instructions.
- Capability inventory: The skill has capabilities to read local files and perform network requests to fetch guidelines.
- Sanitization: No sanitization, escaping, or validation of the input file content is mentioned in the skill definition.
Audit Metadata