The Agent Skills Directory

[SAFE]: The skill implements standard administrative functions for GitHub Actions. A review of the indirect prompt injection surface was conducted since tools like get_run_logs ingest external data while trigger_workflow provides active capabilities. This configuration is consistent with the skill's primary purpose and lacks any malicious patterns or unauthorized behaviors.
[SAFE]: No signs of obfuscation, hardcoded credentials, or unauthorized data exfiltration were found. References to the author's own repositories in examples are consistent with legitimate vendor functionality.

github-actions-management