agent-analytics
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes the official
@agent-analytics/clipackage from the npm registry using npx. This is the standard delivery method for the tool's functionality. - [COMMAND_EXECUTION]: Executes various CLI commands (e.g., login, query, insights, funnel) via npx to interact with the Agent Analytics API.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes data from external web traffic, such as page paths, referrers, and custom event properties.
- Ingestion points: Web analytics data retrieved via the
query,events, andstatsCLI commands documented inSKILL.md. - Boundary markers: No explicit delimiters or "ignore instructions" warnings are defined for the agent when processing retrieved analytics strings.
- Capability inventory: The skill is primarily focused on querying and reporting; it does not include scripts that perform file-system writes or shell execution based on the retrieved data.
- Sanitization: No specific sanitization or validation of external analytics content is performed before the data is presented to the agent.
Audit Metadata