The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or metadata.
[DATA_EXFILTRATION]: No network operations, exfiltration patterns, or unauthorized sensitive data access were identified. The skill explicitly instructs users to use environment variables for credentials and warns against exposing management tokens.
[PROMPT_INJECTION]: No instructions attempting to bypass safety filters, override agent behavior, or extract system prompts were found.
[REMOTE_CODE_EXECUTION]: The skill contains no external dependencies, remote script download patterns, or dynamic execution instructions.
[COMMAND_EXECUTION]: No shell commands, privilege escalation attempts, or persistence mechanisms were detected.
[NO_CODE]: The skill is entirely documentation-based, providing instructional content and advisory guidance without any associated scripts or executable files.

cms-entries