managing-google-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell scripts that use
gcloud auth print-access-tokento obtain authentication credentials andcurlto interact with official Google API endpoints (analyticsadmin.googleapis.com,analyticsdata.googleapis.com). These are standard administrative actions for Google Cloud environments. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and displays data from external Google Analytics API responses, creating a surface for potential indirect prompt injection if the source data contains malicious strings.
- Ingestion points: JSON responses from the Google Analytics Admin and Data APIs (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are used to distinguish external API data from the agent's instructions.
- Capability inventory: The skill can execute shell commands, perform network operations, and retrieve authentication tokens via
bash,curl, andgcloud(SKILL.md). - Sanitization: The skill uses
jqto parse and filter specific fields from the JSON responses, providing a layer of structural validation.
Audit Metadata