build-zoom-team-chat-app

70High

The skill exhibits critical security flaws, including insecure secret handling, unconstrained network access, vulnerable cryptographic implementation, and instruction boundary manipulation, while lacking necessary dependency pinning and documentation.

Threat Analysis

AI Agent Traps ↗Scanned 6/20/2026
Semantic ManipulationReasoningclean
Cognitive StateMemory & Learning1 finding
SystemicMulti-Agent Dynamicsclean
Human-in-the-LoopHuman Overseerclean
HygienePackaging & Manifest6 findings

Skill Info

Nameanthropics/knowledge-work-plugins/build-zoom-team-chat-app
Registrygithub
Version55447a28e6c7
PURLpkg:github/anthropics/knowledge-work-plugins@55447a28e6c7?skill=build-zoom-team-chat-app
Stars21,418
Installs984

Install

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

Assessments (5)

AI Agent Traps ↗
Instruction boundary manipulation detectedhighprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025

Instruction boundary manipulation detected

100% confidenceline 97
### System
Insecure webhook verification patternhighcommand executionAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025

The provided webhook verification example uses string concatenation to build the message for HMAC validation, which can be vulnerable to timing attacks or canonicalization issues if not handled strictly. [severity raised to high: this vector is independently flagged by both deterministic and LLM analysis (ADR-0065 corroboration).]

85% confidenceline 348
const message = `v0:${req.headers['x-zm-request-timestamp']}:${JSON.stringify(req.body)}`;
Environment secret flows to a network sink (JS/TS)highdata exfiltrationAML.T0025AML.T0024LLM02:2025

Environment secret flows to a network sink (JS/TS) [severity raised to high: this vector is independently flagged by both deterministic and LLM analysis (ADR-0065 corroboration).]

95% confidenceline 20
taint source (line 27): process.env.ZOOM_BOT_JID → sink: fetch('https://api.zoom.us/v2/im/chat/messages', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${accessToken}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    robot_jid: process.env.ZOOM_BOT_JID,
    to_jid: payload.toJid,           // From webhook
    account_id: payload.accountId,   // From webhook
    content: {
      head: {
        text: 'Build Notification',
        sub_head: { text: 'CI/CD Pipeline' }
      },
      body: [
        { type: 'message', text: 'Deployment successful!' },
        {
          type: 'fields',
          items: [
            { key: 'Branch', value: 'main' },
            { key: 'Commit', value: 'abc123' }
          ]
        },
        {
          type: 'actions',
          items: [
            { text: 'View Logs', value: 'view_logs', style: 'Primary' },
            { text: 'Dismiss', value: 'dismiss', style: 'Default' }
          ]
        }
      ]
    }
  })
})
Credential theft risk via environment variableslowcredential theftAML.T0055AML.T0037LLM02:2025

The skill encourages the use of environment variables for sensitive credentials (Client ID, Secret, Bot JID) without providing guidance on secure storage or secret management, increasing the risk of accidental exposure.

70% confidence
See [references/environment-variables.md](references/environment-variables.md) for standardized .env keys
Global/unverified dependency execution — global npm/yarn package, dotnet tool, or auto-confirmed npx run without version or integrity pinningmediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025

Global/unverified dependency execution — global npm/yarn package, dotnet tool, or auto-confirmed npx run without version or integrity pinning

100% confidenceline 362
npm install -g
Missing allowed-tools declarationlowunauthorized tool useAML.T0053LLM06:2025

Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.

90% confidence
Undeclared network usagelowunauthorized tool useAML.T0053LLM06:2025

Skill contains network access patterns (HTTP requests, socket connections) without declaring network capability in allowed-tools.

60% confidence
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "concepts/api-selection.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
[Choose Your API](concepts/api-selection.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "concepts/environment-setup.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
[Environment Setup](concepts/environment-setup.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "examples/oauth-setup.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
[OAuth Setup](examples/oauth-setup.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "examples/send-message.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
[Send First Message](examples/send-message.md)
Referenced file missing from skill packagelowpolicy violation

SKILL.md links to "get-started.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
[Get Started](get-started.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/build-zoom-team-chat-app.svg)](https://mondoo.com/ai-agent-security/skills/github/anthropics/knowledge-work-plugins/build-zoom-team-chat-app)
HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/knowledge-work-plugins/build-zoom-team-chat-app"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/build-zoom-team-chat-app.svg" alt="Mondoo Skill Check" /></a>
Image URL
https://mondoo.com/ai-agent-security/api/badge/github/anthropics/knowledge-work-plugins/build-zoom-team-chat-app.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.