canonical-tag
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standard SEO implementation patterns for HTML, Next.js, and server configurations (Apache, Nginx). No suspicious network operations, obfuscation, or remote code execution detected.
- [INDIRECT_PROMPT_INJECTION]: The skill reads local project context files (
.claude/project-context.md,.cursor/project-context.md) to extract site configuration. - Ingestion points: Reads project-specific context files for URL and language structure.
- Boundary markers: None specific, but the usage is limited to identifying project metadata.
- Capability inventory: No subprocess calls, network writes, or file-writing capabilities are present in the skill instructions.
- Sanitization: Standard instructional interpretation by the AI agent.
Audit Metadata