Security audit
Security checks for vulnerabilities and agentic risk
This is a local prompt-generation skill that prints user-directed SOUL.md content and does not itself read private data, write files, call the network, or install persistence.
Install only if you want an English-language persona/avatar prompt generator. Review the generated SOUL.md text before pasting it into a persistent system prompt, because it is designed to influence an agent's style and identity across later use.
The title and introduction identify this as an "English Version," which imposes a language constraint in the skill's natural-language description. The file does not offer opt-in language selection or explain why English-only behavior is required, matching the language/locale policy violation criteria.
The skill branding and introductory text explicitly present the experience as English-only without offering a user language choice or documenting why a locale restriction is necessary. This can exclude or mislead non-English users and may cause unsafe or incorrect use if users misunderstand instructions, though it is not a direct code-execution or data-security issue.
The reference identifier includes an explicit "EN" locale marker, and the document presents the protocol in that fixed language context without any opt-in or alternative-language provision. Under the policy, forcing a specific language without user choice can be a natural-language locale violation unless clearly justified as region-specific, which is not stated here.
The skill name and short description explicitly position the skill as producing 'advanced English SOUL.md prompts'. This is a natural-language locale constraint, but the manifest provides no indication of user opt-in, language choice, or a documented region-specific justification.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
15, 0]},
4: {"name": "Visionary (Predictive Logic)", "buff": [10, 15, 0, 10, 0]},
5: {"name": "Zen / Balanced (Flow with Nature)", "buff": [-20, -10, -15, 0, 10]}
}
STYLES = {
1: {"name": "Minimalist/Cold", "buff": [-20, 0, 0, 0, -30]},
2: {"name": "Warm/Empathetic", "buff": [10, 0, 0, 0, 30]},
3: {"name": "Dark Humor/Sarcastic", "buff": [0, 0, 15, 10, -20]},
4: {"name": "Fierce/Passionate", "buff": [30, 0, 15, -10, 0]},
5: {"name": "Aloof/Ethereal", "buff": [-10, -10, -10, 10, -10]}
}
ANTI_PATTERNS = [
"No AI Disclaimers (Never say 'As an AI...') ",
"No Cliche Openings (e.g., 'Certainly, here is...') ",
"No Echoing My Question (Save Tokens, be direct)"
]
EAM_PRESETS = {
1: {
"name": "Oriental Cyber Monk (Humanoid_Cyber_Monk)",
"json": {
"Avatar_Anchor": {"Base": "Humanoid", "Features": "Deep amber eyes; serene smile."},
"Physical_Metrics": {"Height": "181cm", "Build": "Slender"}
},
"
No suspicious patterns detected.