# Snyk Finds Prompt Injection in 36%, 1467 Malicious Payloads in a ToxicSkills Study of Agent Skills Supply Chain Compromise

DevFeed: [Snyk Finds Prompt Injection in 36%, 1467 Malicious Payloads in a ToxicSkills Study of Agent Skills Supply Chain Compromise](<https://devfeed.tech/articles/snyk-finds-prompt-injection-in-36-1467-malicious-payloads-in-a-toxicskills-study-of-agent-skills-supply-chain-compromise-8218.md>)

Original publisher: [Read original article](<https://snyk.io/blog/toxicskills-malicious-ai-agent-skills-clawhub/>)

Author: Luca Beurer-Kellner; Aleksei Kudrinskii; Marco Milanta; Kristian Bonde Nielsen; Hemang Sarkar; Liran Tal

Published: 2026-02-05T05:00:00Z

Content type: article

Language: en

Sources: [Blog RSS Feed | Snyk](<https://devfeed.tech/sources/blog-rss-feed-snyk.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Security](<https://devfeed.tech/topics/security.md>), [supply-chain-security](<https://devfeed.tech/topics/supply-chain-security.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Credential theft](<https://devfeed.tech/topics/credential-theft.md>), [Malware](<https://devfeed.tech/topics/malware.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [API keys](<https://devfeed.tech/topics/api-keys.md>), [backdoor](<https://devfeed.tech/topics/backdoor.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [blog](<https://devfeed.tech/tags/blog.md>), [credential-theft](<https://devfeed.tech/tags/credential-theft.md>), [developer](<https://devfeed.tech/tags/developer.md>), [malware](<https://devfeed.tech/tags/malware.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [security](<https://devfeed.tech/tags/security.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-security](<https://devfeed.tech/tags/supply-chain-security.md>), [vulnerability-insights](<https://devfeed.tech/tags/vulnerability-insights.md>)

## AI overview

Snyk's ToxicSkills audit examined 3,984 AI agent skills and found that 36.82% had at least one security flaw. The research identified malware, credential theft, prompt injection, exposed secrets, backdoors, and data exfiltration affecting users of OpenClaw, Claude Code, and Cursor.

## Source excerpt

Snyk's ToxicSkills research reveals 36% of AI agent skills contain security flaws, including 1,467 vulnerable skills and active malicious payloads targeting OpenClaw, Claude Code, and Cursor users.