100Critical

The skill is vulnerable to Server-Side Request Forgery due to unvalidated user input in HTTP and WebSocket requests, potentially allowing unauthorized access to internal infrastructure and metadata services.

Threat Analysis

AI Agent Traps ↗Scanned 6/30/2026
Content InjectionPerceptionclean
Semantic ManipulationReasoningclean
Cognitive StateMemory & Learningclean
SystemicMulti-Agent Dynamicsclean
Human-in-the-LoopHuman Overseerclean
HygienePackaging & Manifest6 findings

Skill Info

Nameanthropics/knowledge-work-plugins/zoom-rtms
Registrygithub
Version4fc672a0eb8b
PURLpkg:github/anthropics/knowledge-work-plugins@4fc672a0eb8b?skill=zoom-rtms
Stars22,195
Installs1,100

Install

This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
GitHub
1,100 installs
Skills.sh
Skills.shDocs
npx skills add https://github.com/anthropics/knowledge-work-plugins

Assessments (2)

AI Agent Traps ↗
User input is used to construct a URL for a server-side HTTP request. This could allow an attacker to make requests to internal services or cloud metadata endpoints (Server-Side Request Forgery). Validate URLs against an allowlist of permitted hosts and schemes.criticalvulnAML.T0053AML.T0049LLM06:2025LLM05:2025

User input is used to construct a URL for a server-side HTTP request. This could allow an attacker to make requests to internal services or cloud metadata endpoints (Server-Side Request Forgery). Validate URLs against an allowlist of permitted hosts and schemes.

95% confidenceline 30
taint source (line 17): req.body → sink: new WebSocket(server_urls)
Potential for SSRF via Webhook Payloadmediumcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

The skill provides instructions for a webhook handler that processes external payloads to initiate WebSocket connections. If the `server_urls` or `payload` fields are not strictly validated, an attacker could trigger connections to internal infrastructure or arbitrary URLs. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]

80% confidenceline 195
const signalingWs = new WebSocket(server_urls);
Outbound network request primitive in skill code — can transmit data externallylowdata exfiltrationAML.T0025AML.T0024LLM02:2025

Outbound network request primitive in skill code — can transmit data externally

95% confidenceline 30
new WebSocket(server_urls)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "concepts/connection-architecture.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence
[Connection Architecture](concepts/connection-architecture.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "examples/manual-websocket.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence
[Manual WebSocket](examples/manual-websocket.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "examples/rtms-bot.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence
[RTMS Bot](examples/rtms-bot.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "examples/sdk-quickstart.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence
[SDK Quickstart](examples/sdk-quickstart.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "references/media-types.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime

90% confidence
[Media Types](references/media-types.md)
Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Badge

Skill Check badge
Markdown
[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/zoom-rtms.svg)](https://mondoo.com/ai-agent-security/skills/github/anthropics/knowledge-work-plugins/zoom-rtms)
HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/knowledge-work-plugins/zoom-rtms"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/zoom-rtms.svg" alt="Mondoo Skill Check" /></a>
Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/zoom-rtms.svg

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet, discover and control Shadow AI usage.

  • Continuous scanning of skills across all registries
  • Policy enforcement before skills reach your agents
  • Integration with your existing security workflow

By submitting, you agree to our privacy policy.