seo-off-page-backlinks
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains technical instructions for SEO analysis that are consistent with its stated purpose. All templates, such as outreach emails and disavow file formats, are legitimate industry standards and contain no malicious code or prompt injection triggers.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data (backlink profiles) retrieved through tools like
analyze_backlinks. While this creates a theoretical attack surface where external content could attempt to influence the agent, the risk is inherent to the skill's primary function and no exploitable behaviors were identified. - Ingestion points: External backlink data and domain metrics retrieved via MCP tools (
SKILL.md,README.md). - Boundary markers: The instructions do not explicitly specify delimiters for untrusted external data, but the processing is focused on structured analysis rather than command execution.
- Capability inventory: The skill allows the agent to generate textual outputs such as disavow files (
SKILL.md) and outreach templates (LINK_BUILDING_PLAYBOOKS.md), but provides no access to system commands or dangerous network operations beyond the defined tools. - Sanitization: No specific content filtering is mentioned, which is standard for a purely instructional skill.
Audit Metadata