Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward AI writing helper that passes writing inputs to a configured LLM, with no evidence of hidden persistence, credential access, destructive actions, or exfiltration.
Install only if you are comfortable sending the writing prompts and draft text you provide to whichever LLM implementation you configure. Treat the packaging mismatch as a likely functionality issue that should be fixed before relying on the skill.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
medium: '1000-1500 words',
long: '2000+ words'
};
return guidelines[length] || guidelines.medium;
}
extractTitle(content) {
This skill sends user-influenced content such as topic, audience, key points, outlines, and draft text to the configured LLM multiple times without any explicit disclosure, consent flow, or data-handling notice in the main execution path. In an agent skill context, users may provide proprietary or sensitive text for drafting and refinement, so silent transmission to an external model provider creates a real privacy and data-governance risk even if it is functionally expected.
No suspicious patterns detected.