Back to skill

Security audit

kb-dashboard

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported concerns are either low probability or expected for the skill, but confidence is medium and analysis was incomplete.

The verdict is benign, but the evidence is incomplete: one bundled JavaScript file was only partially inspected, and host runtime permissions were not verified. Consider this uncertainty when deciding whether to install.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (9)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

md
- **离线自包含**:脚本会将包内 `assets/echarts.min.js` 内嵌进产物 HTML,无需联网即可完整渲染全部图表。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 202)May include surrounding context.

md
3. **离线可用·零远程加载**:产物 HTML 已内嵌 ECharts(Apache-2.0),断网双击也能完整渲染;v1.1.1 起不再回退在线 CDN——包内 `assets/echarts.min.js` 缺失时构建报错提示恢复,产物不含任何远程脚本引用。

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 212)May include surrounding context.

md
- `assets/echarts.min.js` — Apache ECharts 5.5.0(Apache-2.0),构建时内嵌进产物,保证离线渲染。

Code capability 'file_read' detected in scripts/build_dashboard.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_read' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

Code capability 'file_write' detected in scripts/build_dashboard.py but not covered by declared permissions.

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_write' capability that is not covered by the declared 'allowed-tools' preapproval. Review the host runtime's actual enforcement policy; runtime permissions are unknown unless separately verified, and this declaration alone does not establish a permission ceiling.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/build_dashboard.py (reported line 167)May include surrounding context.

python
import tempfile, subprocess
        with tempfile.TemporaryDirectory() as td:
            tmp_out = os.path.join(td, "selftest.html")
            r = subprocess.run([sys.executable, os.path.abspath(__file__), "--demo", "--out", tmp_out],
                               capture_output=True, text=True)
            if r.returncode == 0 and os.path.exists(tmp_out) and os.path.getsize(tmp_out) > 100_000:
                h = open(tmp_out, encoding="utf-8").read()