Back to skill

Security audit

Ego Teambition

Security checks for vulnerabilities and agentic risk

Overview

The skill provides disclosed, scoped Teambition access with user confirmation before moving a test case to the recycle bin.

Use the intended Teambition account and verify the selected plan and case before writes. Content updates modify the project case-library record, which may be reused elsewhere. Confirm the case number and title before archiving, and run cleanup when finished. Source inspection resolved the material scanner gaps; the external Ego Lite runtime and live API behavior were not tested.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (9)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk only runs npm test; it shows no login check, browser interaction, or Teambition test-plan or test-case operations. Its visible behavior therefore differs from the declared purpose. Without the package configuration or test script, any underlying actions or resource access remain unknown.

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 27)May include surrounding context.

md
完整技能的方向是 Teambition 管理(项目、任务、测试计划、用例)。`task` 和 `project` 以后挂到同一个 `scripts/tb.mjs` 注册表上,不改路由器。本阶段不做分组创建 / 移动(Phase 2b)和批量(Phase 2c),也不把点页面当主要手段。

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 82)May include surrounding context.

md
已安装的技能目录里用相对路径:`node scripts/check-login.mjs`、`node scripts/tb.mjs testcase …`。

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 135)May include surrounding context.

md
`scripts/lib/session.mjs` 是浏览器 `page.fetch` 门面。Open API 传输调用会失败并说明原因。说明见 `references/transports.md`。字段和坑见 `references/testcase-api.md`、`references/pitfalls.md`。

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/testcase-write-capture.md (reported line 78)May include surrounding context.

md
|------|------|
| `POST /testcase/api/v3/project/{projectId}/testcase/create` | 404 |
| `POST /api/v3/project/{projectId}/testcase/create` | 404 |
| `DELETE /testcase/api/v1/projects/.../testplans/.../testcases/{id}` | 404 |
| `DELETE …/testcases/{id}/delete` | 404 |
| `GET /testcase/api/v1/projects/{projectId}/testhubs` | 404 |
| `GET /api/projects/{projectId}/testhubs` | 404 |

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/test/session.test.mjs (reported line 103)May include surrounding context.

js
test("non-GET fetch sends JSON bodies and leaves archive empty", async () => {
  const posted = fakePage();
  await createPageSession(posted).fetch("https://www.teambition.com/testcase/api/v1/testcases", {
    method: "post",
    body: { title: "新建" },
    timeout: 9,

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/test/session.test.mjs (reported line 115)May include surrounding context.

js
assert.equal(posted.calls.fetch[0].opts.timeout, 9);

  const archived = fakePage();
  await createPageSession(archived).fetch("https://www.teambition.com/api/testcases/abc/archive", {
    method: "POST",
    body: null,
  });

Temporary file creation and deletion occur without disclosure.

Low
Category
Output Handling
Confidence
88% confidence
Finding

The launcher writes a generated script containing the supplied configuration into a temporary directory, then recursively deletes that directory. The supplied file has no comment, docstring, confirmation, or user-facing message explaining these filesystem operations; command-result output does not disclose them.

Content

No source excerpt is available for this finding.