react-composition-patterns
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMMETADATA_POISONING
Full Analysis
- [METADATA_POISONING]: The skill metadata in
SKILL.mdand header inAGENTS.mdattributes the content to "vercel" and "Engineering", which conflicts with the actual author attribution to "secondsky". This discrepancy is a form of deceptive metadata that could mislead users or agents regarding the source and authority of the guidelines.\n- [SAFE]: The code samples provided inAGENTS.mdand therules/directory are standard React patterns (compound components, context API, composition). No executable code, shell commands, or network requests are present in the skill files.
Audit Metadata