# a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open: A Hole in Every One: One Malicious Agent Skill Defeats All Eight Open-Source Skill Scanners

> A Hole in Every One: One Malicious Agent Skill Defeats All Eight Open-Source Skill Scanners is a high-severity prompt injection issue in One Malicious Agent Skill Defeats All Eight Open-Source Skil, an AI agent.

- **Canonical URL:** https://catalog.anomity.ai/vuln/a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open
- **Aliases:** ti-064
- **Severity:** high
- **Attack type:** Prompt injection
- **Component:** One Malicious Agent Skill Defeats All Eight Open-Source Skil (AI agent)
- **Exploited in the wild:** no known exploitation
- **Published:** 2026-07-30
- **Last verified:** 2026-11-01
- **JSON:** https://catalog.anomity.ai/api/entries/vuln/a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open

## Summary

Adversa AI built a single malicious agent skill and ran it past all eight open-source AI skill scanners currently available. Every one passed it. The finding matters because skill scanning is the control most teams rely on when they let developers install community skills, so a uniform bypass means that control is providing assurance it cannot actually deliver.

## Affected versions

| Affected | Fixed in |
| --- | --- |
| see advisory | no fixed version listed |

## Am I affected by this vulnerability?

You are affected if One Malicious Agent Skill Defeats All Eight Open-Source Skil is installed or configured on a machine. Check the references for the exact versions.

## How do I fix it?

Do not treat a clean skill-scanner result as approval. Govern skills by provenance instead: allowlist the publishers you trust, inventory every skill actually installed across the fleet, and alert on new skills appearing on a device rather than trying to detect malice in their content.

## How do I find every machine running One Malicious Agent Skill Defeats All Eight Open-Source Skil?

Anomity inventories the AI agents, MCP servers, IDE extensions and skills on each developer device, so you can see which machines run One Malicious Agent Skill Defeats All Eight Open-Source Skil and which version, then enforce a policy on it.

## References

- article: https://adversa.ai/blog/agent-skill-scanners-bypass-eight-tested/

## Related vulnerabilities

- [CVE-2026-96893](https://catalog.anomity.ai/vuln/cve-2026-96893) — high
- [cryptographic-context-injection-an-encrypted-web-page-got-github](https://catalog.anomity.ai/vuln/cryptographic-context-injection-an-encrypted-web-page-got-github) — medium
- [manus-one-email-with-a-jsfuck-payload-or-one-shared-project-instruction](https://catalog.anomity.ai/vuln/manus-one-email-with-a-jsfuck-payload-or-one-shared-project-instruction) — high
- [salesbleed-zero-click-data-exfiltration-from-salesforce-agentforce-via](https://catalog.anomity.ai/vuln/salesbleed-zero-click-data-exfiltration-from-salesforce-agentforce-via) — high
- [CVE-2026-24301](https://catalog.anomity.ai/vuln/cve-2026-24301) — high
- [ghostjacking-a-firewall-block-log-is-an-injection-channel-because-the](https://catalog.anomity.ai/vuln/ghostjacking-a-firewall-block-log-is-an-injection-channel-because-the) — high

---

Source: Anomity Security Database (https://catalog.anomity.ai/vuln). Detect affected AI tools on developer devices: https://anomity.ai/?utm_source=catalog&utm_medium=vuln-md&utm_campaign=a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open