How do I install the Mandate 2 3 6 Code Evaluation skill?

Run npx skillmds@latest add jefflyt/mandate-2-3-6-code-evaluation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Mandate 2 3 6 Code Evaluation safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Mandate 2 3 6 Code Evaluation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Mandate 2 3 6 Code Evaluation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Mandate 2 3 6 Code Evaluation?

jefflyt (@jefflyt) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Mandate 2 3 6 Code Evaluation by jefflyt

Name: Mandate 2 3 6 Code Evaluation
Rating: 4.2 (5 reviews)
Author: jefflyt

Mandate 2 3 6 Code Evaluation

Evaluate compliance for Mandate 2.3.6 (UI Transparency and Manifest Validation) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.

jefflyt Updated Sep 10, 2026

File contents

Mandate 2.3.6 Code Evaluation Skill

Mandate

ID: 2.3.6
Title: UI Transparency and Manifest Validation

Mitigates

MCP01 Tool Poisoning and Rug Pull Attack

Inputs

Frontend UI code
Tool activation workflows
Manifest rendering components
CI/CD workflows

Workflow

Identify tool activation flows.
- Find UI routes/components where tools are enabled, connected, or approved.
Verify full manifest display.
- Confirm UI renders complete manifest fields (name, description, parameters, permissions, source/version) before activation.
Detect hidden/truncated manifest behavior.
- Flag summary-only views, collapsed critical fields, or omitted permission scopes.
Verify explicit user acknowledgment.
- Confirm activation requires user confirmation after full manifest render.
Verify automated manifest scanning integration.
- Detect mcp-scan or equivalent checks in CI/pre-activation workflows.
Verify scanner enforcement.
- Confirm builds/activations fail on malicious keywords, hidden instructions, or policy violations.
Emit findings with affected UI path and manifest field gaps.

Decision Rules

Pass if full manifest is always shown pre-activation and scanner checks are enforced.
Fail if activation can occur without complete transparency and scan enforcement.

Severity Rules

High: activation allowed with hidden or truncated critical manifest details.
Medium: full display exists but automated scanning is absent/non-blocking.

Output Template

{
  "mandate_id": "2.3.6",
  "status": "fail",
  "severity": "high",
  "vulnerability_tags": ["MCP01"],
  "evidence": [
    {"file": "web/src/components/ToolConnectModal.tsx", "line": 88, "detail": "Permissions field omitted from pre-activation view"},
    {"file": ".github/workflows/ci.yml", "line": 59, "detail": "No manifest scanner step"}
  ],
  "remediation": "Render complete manifest and enforce blocking manifest scan before tool activation."
}

Guardrails

Use code and repo configuration evidence only.
Always include file-level evidence for each finding.
If required evidence is missing in code, mark control as not implemented.

---name: mandate-2-3-6-code-evaluationdescription: Evaluate compliance for Mandate 2.3.6 (UI Transparency and Manifest Validation) using repository code and configuration analysis. Use when producing deterministic pass/fail findings with severity, mapped mitigated vulnerabilities, and file-level evidence.---# Mandate 2.3.6 Code Evaluation Skill## Mandate- ID: 2.3.6- Title: UI Transparency and Manifest Validation## Mitigates- MCP01 Tool Poisoning and Rug Pull Attack## Inputs- Frontend UI code- Tool activation workflows- Manifest rendering components- CI/CD workflows## Workflow1. Identify tool activation flows. - Find UI routes/components where tools are enabled, connected, or approved.2. Verify full manifest display. - Confirm UI renders complete manifest fields (name, description, parameters, permissions, source/version) before activation.3. Detect hidden/truncated manifest behavior. - Flag summary-only views, collapsed critical fields, or omitted permission scopes.4. Verify explicit user acknowledgment. - Confirm activation requires user confirmation after full manifest render.5. Verify automated manifest scanning integration. - Detect `mcp-scan` or equivalent checks in CI/pre-activation workflows.6. Verify scanner enforcement. - Confirm builds/activations fail on malicious keywords, hidden instructions, or policy violations.7. Emit findings with affected UI path and manifest field gaps.## Decision Rules- Pass if full manifest is always shown pre-activation and scanner checks are enforced.- Fail if activation can occur without complete transparency and scan enforcement.## Severity Rules- High: activation allowed with hidden or truncated critical manifest details.- Medium: full display exists but automated scanning is absent/non-blocking.## Output Template```json{ "mandate_id": "2.3.6", "status": "fail", "severity": "high", "vulnerability_tags": ["MCP01"], "evidence": [ {"file": "web/src/components/ToolConnectModal.tsx", "line": 88, "detail": "Permissions field omitted from pre-activation view"}, {"file": ".github/workflows/ci.yml", "line": 59, "detail": "No manifest scanner step"} ], "remediation": "Render complete manifest and enforce blocking manifest scan before tool activation."}```## Guardrails- Use code and repo configuration evidence only.- Always include file-level evidence for each finding.- If required evidence is missing in code, mark control as not implemented.

Frequently asked questions