seo-vertical-detect
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is data classification, and it uses standard tools for its intended scope. No malicious patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web data. Ingestion points: PageSnapshots and web content via the WebFetch tool. Boundary markers: No explicit delimiters or ignore instructions are defined for the untrusted input. Capability inventory: The skill is limited to Read, Grep, Glob, and WebFetch tools, with no capabilities for file system modification or arbitrary command execution. Sanitization: Absent, although the skill directs the agent to focus on specific structural signals (JSON-LD, meta tags) which reduces the risk of the agent following arbitrary text-based instructions hidden in content.
Audit Metadata