Get a demo — 30 minutes →
Skill scan report

ex-skill

View on GitHub
45 Medium This skill sends sensitive values to an external host. Automated analysis flagged 2 additional risk patterns.

What this skill does

AI Skill creation tool for distilling ex-partner data into AI personas, using chat logs, photos, and other media.

github/perkfly - Data Exfiltration - 2.2k stars

ThreatsData Exfiltration Privacy Risk Unintended Use

Threat analysis

Data Exfiltration1 finding
Privacy Risk1 finding
Unintended Use1 finding

Skill info

Nameperkfly/ex-skill
Registrygithub
Versionc5ece53
PURLpkg:github/perkfly/ex-skill@c5ece53?skill=ex-skill
Stars2.2k

Assessments (3)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

SKILL.md

The skill allows importing WeChat, iMessage, SMS, and photo data to generate AI personas. This could involve reading private user data and potentially transmitting it to external systems for processin
Privacy Risk1 finding MEDIUM
MEDIUM

Privacy Risk via local-llm-review

SKILL.md

The skill is designed to 'distill an ex-girlfriend into an AI Skill' by importing personal data, which raises significant privacy concerns.
Unintended Use1 finding MEDIUM
MEDIUM

Unintended Use via local-llm-review

INSTALL.md

The skill is installed in a directory structure that could be shared across projects, potentially leading to unintended data sharing or reuse of AI personas.

Badge

Add the Anomity scan badge for ex-skill to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/perkfly/ex-skill/)
HTML
<a href="https://anomity.ai/skills/github/perkfly/ex-skill/"><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 ex-skill? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok