Security audit
Security checks for vulnerabilities and agentic risk
This is a document-only short-video audio guide with no executable code, network access, credential handling, or persistence.
Before installing, consider narrowing the trigger phrases if your environment has many audio-related skills. Otherwise, this skill appears proportionate for informational guidance and does not request sensitive access.
The trigger keywords are very broad and generic for common media tasks, which can cause the skill to activate in contexts beyond its intended scope. Over-broad invocation increases the chance of accidental routing, prompt interference, or misuse of the skill in unrelated conversations, though this README itself does not contain directly dangerous functionality.
The trigger keywords are generic audio terms that can match many ordinary user requests unrelated to this skill’s intended scope, increasing the chance of accidental invocation. Over-broad activation can cause the wrong skill to respond, creating confusion, poor task routing, and potentially bypassing more appropriate safeguards or domain-specific handling in a larger agent system.
This manifest file defines trigger keywords such as "audio recording," "video sound," and "audio quality" without any limiting context, exclusions, or negative examples. These phrases are generic enough to match common user requests beyond this specific skill, which can cause unintended activation.
Line L07 states 'English-first documentation,' which imposes a language preference in natural language. The file does not indicate that users may choose another language or provide a documented region-specific justification for this constraint.
The document is primarily in English but includes a full Chinese usage scenario and expected output without stating that the skill supports multilingual responses based on user preference. This can create a language/locale policy issue because the skill appears to switch languages without an explicit documented opt-in mechanism.
The file specifies "language": "en" with no surrounding documentation indicating that English is optional, user-selected, or required for a justified region-specific purpose. This can violate language/locale policy expectations when a skill imposes a language without user opt-in.
No suspicious patterns detected.
