google-reviews
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a shell command to execute a local Node.js script with arguments provided by the user (business name and location). This creates a potential surface for command injection if these inputs are not sanitized before being executed in a shell environment.
- [EXTERNAL_DOWNLOADS]: The skill mentions the use of
npm installto set up its execution environment. This involves downloading third-party packages from the official npm registry. - [PROMPT_INJECTION]: The skill retrieves and processes external data (business reviews and names) from the DataForSEO API, which is an untrusted source that could contain malicious instructions designed to manipulate agent behavior.
- Ingestion points: Business data and ratings fetched from the DataForSEO API specified in the 'API Details' section of SKILL.md.
- Boundary markers: No delimiters or instructions are specified to help the agent distinguish between data and potentially malicious embedded instructions.
- Capability inventory: The skill allows the execution of local shell commands via the
nodescript execution mentioned in the 'Usage' section. - Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from the API.
Audit Metadata