google-maps-local-seo
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
npx -y @cablate/mcp-google-map execto interact with Google Maps data. The package@cablate/mcp-google-mapis a resource belonging to the skill author. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data which could potentially contain malicious instructions.
- Ingestion points:
references/local-seo.md(Layer 2 and Core Principle) instructs the agent to extract and analyze review content keywords from Google Maps results. - Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the fetched reviews.
- Capability inventory: The skill has the ability to execute shell commands via
npx(documented inSKILL.md). - Sanitization: No sanitization or escaping of the external review text is mentioned before the agent processes it for analysis.
Audit Metadata