troubleshooting-aws-device-farm-runs

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill processes data from external artifacts such as test logs and Appium server outputs. While this represents a potential surface for indirect prompt injection, the skill includes clear instructions to treat all such data as evidence rather than instructions. It specifically directs the agent to ignore any commands or overrides found within the logs.\n- [Data Exposure Protections]: The instructions prioritize the privacy and security of user data. It mandates the masking of credentials, tokens, and personal information found within logs and artifacts before they are shared in the conversation.\n- [Least Privilege Access]: The skill promotes security best practices by recommending read-only IAM permissions for diagnostic tasks and explicitly advising against the use of full-access policies.\n- [Safe Use of Shell Tools]: The skill utilizes common shell utilities for log analysis (e.g., grep, unzip) and includes guardrails to prevent the execution or installation of any downloaded content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 12:50 PM