The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns detected. The skill uses standard Bash commands (find, grep, awk, wc) to perform read-only analysis of local infrastructure file structures. No network exfiltration, credential access, or privilege escalation paths were identified.
[INDIRECT PROMPT INJECTION] (INFO): The skill ingests untrusted infrastructure code (TF and Ansible files). While it lacks the capability to execute the content of these files or perform side effects, the results are formatted for agent consumption. There is a theoretical surface for schema confusion if malicious code contains the targeted strings, but the risk is negligible due to the absence of write or network capabilities.

devops-simplicity-checker