image-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and does not contain any malicious patterns, obfuscation, or dangerous command execution. All code snippets provided are static examples for HTML, XML, and JSON-LD implementation.
- [INDIRECT_PROMPT_INJECTION]: The skill checks for project-specific context files to provide tailored SEO recommendations.
- Ingestion points: Reads
.claude/project-context.mdand.cursor/project-context.md(SKILL.md) - Boundary markers: None
- Capability inventory: None (The skill defines no tools or executable scripts)
- Sanitization: Not applicable as no processing or execution is performed on the ingested data.
Audit Metadata