local-seo-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted data from business websites and directory listings.\n
- Ingestion points: Data is retrieved from target business websites using tools like
web_fetchorcurl, and from Google Business Profile reviews and metadata.\n - Boundary markers: There are no instructions for using delimiters or explicit security markers to separate external data from the agent's internal instructions.\n
- Capability inventory: The agent uses the
localseodata-toolfor specialized audit tasks and general network fetching tools to access website content for technical review.\n - Sanitization: The skill does not include steps for sanitizing or validating external HTML or text content before the agent processes it, which is a standard attack surface for skills of this nature.
Audit Metadata