Security audit
Security checks for vulnerabilities and agentic risk
This skill is not clearly malicious, but it can save information to a knowledge base from broad trigger phrases and relies on missing external code that was not available for review.
Install only if you are comfortable with a skill that may persist AI-video-related notes to a knowledge base. Review or narrow the trigger phrases, require confirmation before saving, and verify the external capability implementation before using it in a real environment.
The trigger phrases at these lines are very broad natural-language phrases that can match common user requests unrelated to this skill. Because the skill writes summaries into a knowledge base and links to other components, an accidental trigger could cause unintended persistence of content or execution of downstream workflow behavior.
The trigger uses the keyword 'Topaz', which is overly generic and likely to collide with ordinary conversation, product discussion, or unrelated assistance requests. In this skill, such a collision could incorrectly activate learned workflow content and save or act on information the user did not intend to store.
No suspicious patterns detected.
