Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only Spanish content-repurposing skill with disclosed file-saving and Telegram-summary behavior, and no evidence of malicious code, persistence, or hidden data exfiltration.
Install this if you want a Spanish-language helper for repurposing scripts into content formats. Be aware it may use profile or Segundo Cerebro context to identify your industry, save generated pieces under guiones/, and send a summary through Telegram in an OpenClaw setup.
The trigger definition is overly broad and can cause the agent to activate this skill for loosely related requests, leading to misrouting and unintended behavior. In a multi-skill agent, that can override more appropriate skills or inject irrelevant instructions into unrelated conversations, reducing reliability and potentially affecting safety-critical routing decisions.
The skill content and activation guidance are entirely in Spanish and do not offer a language fallback or user-choice mechanism. This can cause the agent to respond in the wrong language or apply Spanish-first instructions to users who did not opt in, creating usability issues and increasing the chance of misunderstanding user intent.
This file presents all user-facing guidance in Spanish and does not indicate that the skill is limited to Spanish-speaking users or provide an opt-in language choice. Under the language/locale policy, forcing a specific language without user choice can be a natural-language policy issue.
No suspicious patterns detected.
