The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute ffmpeg and ffprobe shell commands to perform video transformation and metadata validation.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests untrusted user data including headlines (text), background hex codes, and video/logo files.
Boundary markers: None. The instructions do not define delimiters or specific 'ignore instructions' guards for the user-supplied content.
Capability inventory: The agent utilizes ffmpeg and ffprobe via the command line, providing a path for command injection if inputs are not handled carefully.
Sanitization: There are no instructions for escaping or validating the headline text or background color hex codes before they are used in the ffmpeg filter string, creating a vulnerability where a malicious user could attempt to break out of the command context.

reel-export