The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests data from external videos and social posts using tools like watch-video and social-fetch, creating an indirect prompt injection surface.
Ingestion points: External media and social metadata are processed from untrusted URLs.
Boundary markers: None are specified to separate external content from the agent's core instructions.
Capability inventory: The skill generates code and executes shell commands for video rendering.
Sanitization: There are no explicit steps for sanitizing content extracted from external sources.
[COMMAND_EXECUTION]: The skill uses npm and npx to install and run video frameworks like hyperframes and remotion, which are legitimate tools for its intended purpose.

video