ga4-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Google Analytics 4 APIs, which could theoretically contain malicious instructions if the GA4 property or event parameters are controlled by an attacker.
- Ingestion points: Data enters the context via
mcp__cogny__google_analytics_4__tool_get_metadata,mcp__cogny__google_analytics_4__tool_get_property, andmcp__cogny__google_analytics_4__tool_run_reportas described in SKILL.md. - Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" wrappers for the data fetched from the GA4 API.
- Capability inventory: The skill uses
mcp__cogny__create_findingto write audit results to an external system and generates a summary report for the user. - Sanitization: No explicit sanitization or validation of the API-returned strings is defined in the instruction set.
Audit Metadata