The Agent Skills Directory

[SAFE]: The skill defines a legitimate and structured interface for DaVinci Resolve integration. No evidence of obfuscation, hardcoded credentials, malicious remote code execution, or unauthorized data exfiltration was found.
[COMMAND_EXECUTION]: The skill utilizes a set of specialized tools (resolve_control, project_manager, script_plugin) to interact with the DaVinci Resolve environment and file system. These operations are restricted to the primary purpose of video post-production workflows.
[PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill is designed to analyze external media and project files (.drp, .drt, .drx). While these files could theoretically contain malicious metadata, the skill provides specific instructions for safe handling, such as preserving recoverable versions and adhering to defined sidecar output paths.
[REMOTE_CODE_EXECUTION]: The skill provides mechanisms to manage extensions (Fuse, DCTL, Lua, and Python plugins) through the script_plugin tool. This is a standard requirement for DaVinci Resolve pipeline automation and is documented as a project lifecycle feature.

resolve-mcp