seo-offpage
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidance and templates for SEO professionals. All logic and documentation are focused on link-building strategies and digital PR. The referenced files are local markdown documents containing benign text templates and educational guides.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external backlink data (such as referring domains and anchor text) from third-party SEO tools. While this represents a surface for indirect prompt injection due to the ingestion of untrusted external content, the impact is restricted to the generated reports. The skill does not possess capabilities to execute code, access sensitive system files, or perform unauthorized network operations based on the processed data.\n
- Ingestion points: Workflow step 1 in SKILL.md identifies Ahrefs, Semrush, Moz, and Majestic as sources for referring domain and anchor text data.\n
- Boundary markers: The framework does not explicitly instruct the agent to use specific delimiters when processing tool-provided data.\n
- Capability inventory: The skill's functionality is limited to producing strategy documents (offpage-strategy.md) and spreadsheet-based tracking lists. It does not have access to shell execution, privilege escalation, or direct network exfiltration tools.\n
- Sanitization: The instructions do not provide specific methods for sanitizing or filtering input from external SEO tools.
Audit Metadata