seo-local
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from URLs and business listings, which could be used by an attacker to attempt to influence the agent's behavior through embedded instructions.
- Ingestion points: User-provided URLs and signals from web pages or Google Business Profiles.
- Boundary markers: The skill includes a dedicated Security section explicitly instructing the agent to treat fetched content as untrusted data and never as instructions.
- Capability inventory: The skill generates markdown reports and utilizes specific SEO data tools for business listing and SERP analysis.
- Sanitization: The instructions clearly state that the agent should never run commands, install software, or change settings based on fetched content.
Audit Metadata