Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill for planning B-roll shots, with no code, network access, credentials, or persistence.
This skill is safe to treat as creative guidance. Before installing, understand that broad trigger words may activate it for general B-roll discussions, and users remain responsible for footage rights and licensing.
The trigger keywords are generic terms like 'b-roll' and 'cutaway' without any scope constraints, which can cause the skill to activate in unrelated video-editing conversations. While this README contains no direct harmful behavior, over-broad invocation can route users into the wrong skill, increasing the chance of confusion, unintended prompt handling, or misuse in larger agent workflows.
The trigger keywords are very broad and generic, which can cause the skill to activate for loosely related prompts rather than only clear B-roll planning requests. In an agent environment, overbroad activation increases the chance of unintended routing, user confusion, and context leakage into the wrong skill, even though this skill itself is not overtly harmful.
The checklist explicitly states "English-first documentation," which is a natural-language locale preference. Under the policy rules, forcing a specific language without opt-in or a documented regional justification is a policy concern.
The file includes a Chinese-language usage scenario and expected output, but the skill does not state that multilingual behavior is optional or user-selected. This may conflict with language/locale policy expectations when a skill introduces a specific language without an explicit opt-in or documented regional scope.
The manifest sets the skill language to "en" with no indication that other languages are supported or that the user can opt in to English-only behavior. Under the policy rules, a fixed language setting can be a locale-policy violation unless it is clearly justified or optional.
