integrate-arcjet-guard-google-adk-py
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the 'arcjet' library with the 'google-adk' extra. These are official packages provided by the skill's author and are standard for the described integration.
- [COMMAND_EXECUTION]: Contains instructions for standard library installation using 'pip' or 'uv'. These commands are expected for development environment setup.
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for screening user input to detect malicious content.
- Ingestion points: The 'user_text' variable in the SKILL.md examples represents untrusted data entering the agent context.
- Boundary markers: The instructions recommend using a security guard (DetectPromptInjection) to evaluate content rather than using text-based delimiters.
- Capability inventory: The runner executes tools and model calls through the google-adk framework as described in the examples.
- Sanitization: The skill utilizes the 'server_input' helper from the vendor library to type and validate input data.
Audit Metadata