seo-fix-plan
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with UnifAPI endpoints (including
browser/*andseo/*) to fetch live search and website data. These are vendor-provided services necessary for the skill's core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites (HTML/Markdown) to identify SEO issues. While this presents a theoretical attack surface, the skill's design is restricted to generating a textual report ("eyes not hands"), which prevents automated exploitation or unauthorized system changes.
- [COMMAND_EXECUTION]: The provided skill files do not contain any shell commands, subprocess calls, or system-level execution patterns.
Audit Metadata