The Agent Skills Directory

[SAFE]: The skill provides documentation for a framework belonging to a trusted organization. No malicious patterns were detected.
[EXTERNAL_DOWNLOADS]: The skill references the google-adk package and GitHub repositories within the google organization. These are documented neutrally as they originate from a recognized trusted service and align with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill requires standard development tools such as Bash and Read/Write to facilitate agent development and execution of the ADK CLI (adk run). These capabilities are appropriate for the skill's primary use case as an agent engineering toolkit.
[PROMPT_INJECTION]: The skill describes an agent architecture that processes user input (LlmAgent). While this represents a standard attack surface for indirect prompt injection common to all LLM-based applications, the skill does not introduce specific vulnerabilities or override safety guidelines.

google-adk