The Agent Skills Directory

[SAFE]: The skill provides technical documentation and code templates for writing BlinkScript kernels in Nuke. All identified code patterns, such as pixel access and GPU optimization techniques, follow official developer guidelines from Foundry.
[SAFE]: No evidence of prompt injection or attempts to override agent safety protocols was detected in the skill instructions or metadata.
[SAFE]: No hardcoded credentials, sensitive file path exposure, or unauthorized data exfiltration patterns were found. References to local application directories (~/.nuke) are standard for Nuke-related development and do not involve credential harvesting.
[SAFE]: The skill does not perform any remote code execution or download external dependencies. It references official Foundry documentation and well-known community guides.
[SAFE]: No obfuscation techniques, including Base64 encoding, zero-width characters, or homoglyph attacks, were detected in the source code or documentation.
[SAFE]: No persistence mechanisms, privilege escalation attempts, or dynamic context injection patterns (e.g., !command syntax) were found in the skill files.

nuke-blinkscript