seo-audit
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's files. The skill correctly utilizes localized context files and follows platform-specific patterns for multi-agent task delegation.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to process content from external websites (such as metadata, headers, and on-page content) during the audit process. Ingestion points: Content from the target URL and search engine results are interpolated into prompts for the 'Explore' subagents in SKILL.md. Boundary markers: The prompts for technical and content analysis lack explicit delimiters to isolate external site data from the subagent's instructions. Capability inventory: The skill has the capability to read local context files and initiate subagent tasks. Sanitization: No explicit sanitization or escaping of the fetched website content is performed before it is passed to subagents.
Audit Metadata