google-adk-python
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and Python code snippets from Google's official GitHub repository (
google/adk-docs) to provide users with up-to-date technical guidance. - [COMMAND_EXECUTION]: The skill instructions suggest using
curlvia shell commands to retrieve the content of documentation files from trusted external URLs. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content from documentation links, which represents an ingestion surface for potential instructions embedded in that data.
- Ingestion points: Reference URLs in files such as
references/agents.md,references/tools.md, andreferences/streaming.mdpointing to GitHub raw content. - Boundary markers: None identified in the provided instructions; the agent is directed to read the content to explain concepts to the user.
- Capability inventory: Includes the ability to fetch web content and run shell commands (
curl) to retrieve data. - Sanitization: No specific sanitization or filtering logic is defined for the fetched content before it is processed by the agent.
Audit Metadata