schema-markup
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill prompts the agent to read .claude/project-context.md and .cursor/project-context.md to gather product and content information. This creates an attack surface where untrusted data within those files could influence agent output. (Ingestion points: project-context.md files; Boundary markers: absent; Capability inventory: code generation and guidance; Sanitization: absent).
- [SAFE]: The skill includes numerous links to official documentation from Google, Bing, and Schema.org. These target trusted organizations and well-known services for the purpose of valid schema implementation and testing.
Audit Metadata