Book a 30-minute demo →
Skill scan report

soul-archive

View on GitHub
49 Medium Automated analysis flagged 5 potential risk patterns.

What this skill does

Digital personality persistence system that collects user data during conversations to create a digital clone of the user's personality.

github/leoyeai - Data Collection Risk - 2.1k stars

ThreatsData Collection Risk Data Persistence Risk Data Storage Risk Privacy Risk Surveillance Risk

Threat analysis

Data Collection Risk1 finding
Data Persistence Risk1 finding
Data Storage Risk1 finding
Privacy Risk1 finding
Surveillance Risk1 finding

Skill info

Nameleoyeai/soul-archive
Registrygithub
Versione5199b5
PURLpkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=soul-archive
Stars2.1k

Assessments (5)

Data Collection Risk1 finding HIGH
HIGH

Data Collection Risk via local-llm-review

SKILL.md

The system collects 'sensitive topics' including health, finances, and intimate relationships, with no clear opt-out mechanism for users who may not want their data collected in these areas.
Data Persistence Risk1 finding HIGH
HIGH

Data Persistence Risk via local-llm-review

SKILL.md

The system creates a digital soul clone that can 'act on the user's behalf' and 'continue conversations after their death.' This implies the system is designed for long-term persistence of personal da
Data Storage Risk1 finding HIGH
HIGH

Data Storage Risk via local-llm-review

scripts/soul_init.py

The system stores data in the user's home directory (~/.skills_data/soul-archive/), which may be accessible to other applications or users with access to the same machine, despite claims of 'privacy f
Privacy Risk1 finding HIGH
HIGH

Privacy Risk via local-llm-review

SKILL.md

The skill collects and stores highly sensitive personal information including: speaking habits, knowledge and views, personal information (identity, experiences, relationships, life details), personal
Surveillance Risk1 finding HIGH
HIGH

Surveillance Risk via local-llm-review

SKILL.md

The system collects data 'silently' without interrupting the conversation flow or asking for explicit consent, which could be considered a form of passive surveillance.

Badge

Add the Anomity scan badge for soul-archive to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/leoyeai/soul-archive/)
HTML
<a href="https://anomity.ai/skills/github/leoyeai/soul-archive/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

How Anomity governs this at runtime

Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.

Book a 30-minute demo to see your own skill inventory.

Methodology and disputes

Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of soul-archive? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok