seo-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate SEO guidelines and audit instructions. All code examples are standard implementation patterns for web development.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it audits user-provided codebase content.
- Ingestion points: Codebase files and page layouts identified via user arguments or project scanning during an audit (SKILL.md).
- Boundary markers: Absent; the instructions do not explicitly provide delimiters or specific "ignore" commands for instructions embedded within audited files.
- Capability inventory: The potential for exploitation is limited by the skill's strict output requirement (PASS/FAIL/N/A), which helps prevent the agent from executing instructions found in the codebase.
- Sanitization: No sanitization or filtering is performed on the code content during the audit process.
Audit Metadata