Book a 30-minute demo →
Skill scan report

defipoly

View on GitHub
49 Medium Automated analysis flagged 4 potential risk patterns.

What this skill does

Game agent for a DeFi-based Monopoly-inspired game on Solana. The agent autonomously plays the game using a funded Solana wallet.

github/leoyeai - Excessive Agency - 2.1k stars

ThreatsExcessive Agency Least Privilege Supply Chain

Threat analysis

Excessive Agency2 findings
Least Privilege1 finding
Supply Chain1 finding

Skill info

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

Assessments (4)

Excessive Agency2 findings HIGH
HIGH

Excessive Agency via local-llm-review

scripts/agent-play.js

The agent is described as playing autonomously with a funded SOL wallet, which implies it may perform actions without explicit user input or oversight.
MEDIUM

Excessive Agency via local-llm-review

SKILL.md

The skill's description states that the agent 'plays autonomously with a funded SOL wallet', which could imply uncontrolled or unmonitored actions on the user's behalf.
Least Privilege1 finding MEDIUM
MEDIUM

Least Privilege via local-llm-review

SKILL.md

The skill's description does not specify any limitations on the agent's actions, which could imply it has excessive permissions.
Supply Chain1 finding LOW
LOW

Supply Chain via local-llm-review

package.json

The package.json file includes third-party dependencies such as '@solana/web3.js', 'bs58', and 'tweetnacl', which could introduce potential security risks if not properly vetted.

Badge

Add the Anomity scan badge for defipoly to your README.

Anomity Skill Check badge

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

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok