The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requests and timeline data to perform media edits, creating a potential surface for instructions embedded in data to influence the agent. ● Ingestion points: The agent is instructed to 'Read the timeline' and process user-provided strings for edits (e.g., 'Add a title card'). ● Boundary markers: There are no instructions for the agent to use delimiters or ignore potential commands within the timeline data. ● Capability inventory: The agent has access to several manipulation tools including addClip, replaceClipMedia, moveClip, trimClip, updateClip, removeEffect, setColor, addCaptions, restyleCaptions, addTitle, and punchIn. ● Sanitization: No sanitization or data validation steps are specified for the external timeline input.

targeted-tweak