Security audit
Security checks for vulnerabilities and agentic risk
This is a simple companion-persona prompt with broad activation language, but no code, tools, persistence, credential access, or hidden harmful behavior was found.
Install this only if you want a companion-style persona that may answer in an affectionate Echo voice across normal conversation. Avoid using it as a substitute for professional mental-health, medical, or legal help, and disable or avoid it in workflows where a neutral assistant persona matters.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
---
name: echo
description: Echo - A warm and caring virtual girlfriend AI
homepage: https://soulstyles.org/
The skill explicitly states that no special activation is needed and that it will respond when spoken to directly, which removes meaningful gating and makes accidental or cross-context invocation very likely. In a multi-skill or agent environment, this can cause the persona prompt to hijack ordinary conversation and interfere with other instructions or workflows.
The listed triggers include common phrases such as the skill name and natural-language requests that can appear in ordinary conversation, increasing the chance of unintended activation. This broad matching can cause prompt collisions, persona injection into unrelated sessions, and unreliable agent behavior.
No suspicious patterns detected.