The Agent Skills Directory

[SAFE]: The skill uses environment variables ($IBLAI_API_KEY, $IBLAI_ORG, $IBLAI_USERNAME) for authentication and context, avoiding hardcoded secrets and following standard security practices.
[SAFE]: All network operations are directed to the vendor's official platform API at api.iblai.app, which is consistent with the skill's stated purpose of managing ibl.ai agent sandboxes.
[SAFE]: The instructions explicitly require the agent to confirm with the user before performing destructive actions, such as disconnecting or deleting sandbox instances.
[SAFE]: No evidence of prompt injection, obfuscation, unauthorized data exfiltration, or malicious remote code execution was identified during the analysis.

iblai-agent-sandbox