The Agent Skills Directory

[SAFE]: The skill was analyzed for common threat vectors including prompt injection, data exfiltration, and remote code execution, with no malicious patterns identified.
[NO_CODE]: The provided file is a markdown instruction set without any accompanying scripts, binaries, or automated shell commands.
[PROMPT_INJECTION]: The skill processes user-provided or externally generated video briefs. This represents an indirect prompt injection surface; however, the impact is negligible as the skill's capabilities are limited to generating text outlines and visual aid lists, with a workflow that includes human confirmation steps. 1. Ingestion points: Video briefs (referenced as output from /youtube-brief or user input). 2. Boundary markers: Absent. 3. Capability inventory: Generating and saving markdown text files. 4. Sanitization: Absent.

youtube-outline