Security audit
Security checks for vulnerabilities and agentic risk
This skill is a standalone creative prompt for turning conversation context into visual direction, with no executable code or hidden data access.
Before installing, understand that the skill may synthesize the current conversation by default, so use it when you are comfortable turning that context into a creative visual guide. I found no evidence of file access, network transmission, persistence, or executable behavior.
Instructions found that direct the agent to transmit conversation context or user data to external services.
**What this skill does NOT do:**
- Read files from the workspace
- Access project artifacts directly
- Send data to external services
- Call image generation APIs
**Output behavior:**
The trigger description combines explicit invocation with 'when deep technical insight emerges,' which is subjective and does not define clear activation boundaries. Because no concrete criteria or negative examples are given for what counts as 'deep technical insight,' agents may invoke the skill inconsistently or too broadly.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
**What this skill does NOT do:**
- Read files from the workspace
- Access project artifacts directly
- Send data to external services
- Call image generation APIs
**Output behavior:**
The trigger line uses Japanese-only phrasing '明示呼出 (explicit invocation)' in a way that may imply a language-specific invocation convention, but the document does not state that language choice is optional or region-specific. This can create a locale-policy concern because users are not explicitly offered a language or phrasing choice.
No suspicious patterns detected.