The Agent Skills Directory

[SAFE]: The skill instructions and documentation do not contain any malicious directives, credential harvesting, or suspicious network operations.
[NO_CODE]: This skill consists entirely of markdown instructions and configuration metadata. It does not include any executable scripts or binaries, significantly reducing its security risk profile.
[COMMAND_EXECUTION]: The skill instructs the agent to use yt-dlp for video downloading and analysis. This is a functional requirement for the skill's purpose and uses a well-known media processing utility.
[PROMPT_INJECTION]: The skill is designed to process untrusted external content (videos and linked pages).
Ingestion points: External video URLs and downloaded media files (SKILL.md).
Boundary markers: No specific delimiters or instructions are provided to separate analyzed content from the agent's core operational logic.
Capability inventory: The agent utilizes yt-dlp to interact with the network and local file system (SKILL.md).
Sanitization: There is no evidence of filtering or sanitization of content retrieved from external sources.

viral-analysis