meta-title
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified. The skill acts as a static reference for SEO best practices.
- [NO_CODE]: The analyzed files consist exclusively of markdown documentation and instructional guidelines without any associated scripts or executable components.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze external HTML metadata, creating a surface for potential instruction injection from untrusted sources. 1. Ingestion points: Instructions in
SKILL.mddirect the agent to inspect<title>tags in page headers. 2. Boundary markers: Not present; the instructions do not include specific delimiters for the external content. 3. Capability inventory: The skill itself lacks execution, file system, or network capabilities. 4. Sanitization: No sanitization is performed on the ingested HTML content.
Audit Metadata