ClawHub
Back to skill

Security audit

Alibaba Cloud Media Live

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently supports Alibaba Cloud Live management, but users should take care not to save credentials or sensitive request details in its evidence files.

Install only if you intend to let an agent help manage Alibaba Cloud Live resources. Use least-privilege STS/RAM credentials, confirm the exact region/domain/app/stream before mutations, and redact credentials, Authorization data, signatures, tokens, signed URLs, and sensitive identifiers before saving evidence under output/aliyun-live-manage/.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (12)

Tainted flow: 'timeout' from os.getenv (line 30, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
def fetch_json(url: str, timeout: int) -> dict:
    req = urllib.request.Request(url, headers={"User-Agent": "codex-skill"})
    with urllib.request.urlopen(req, timeout=timeout) as resp:
        return json.loads(resp.read().decode("utf-8"))
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding
The skill is described as managing live resources and workflows, but the visible behavior centers on metadata discovery, documentation fetching, and local artifact generation. This mismatch can mislead operators and policy engines about what the skill actually does, causing it to be invoked in contexts with broader trust or permissions than warranted.

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill uses environment credentials, writes files, and performs network access, but it does not declare any explicit tool scope or permission boundaries. In an agent setting, this increases the chance of unintended capability use and makes review and enforcement of least privilege harder.

Session Persistence

Medium
Category
Rogue Agent
Content
## Validation

```bash
mkdir -p output/aliyun-live-manage
python -m py_compile skills/media/live/aliyun-live-manage/scripts/list_openapi_meta_apis.py
echo "py_compile_ok" > output/aliyun-live-manage/validate.txt
```
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs saving request parameters, region, domain, and stream context as execution evidence without any filtering guidance. In cloud-management workflows, those artifacts can contain sensitive identifiers, operational topology, or even secrets if callers include tokens or signed parameters.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs use of AccessKey/STS credentials but does not warn against logging, persisting, or echoing them into output artifacts. Because the workflow also emphasizes evidence capture and local file writes, there is a realistic risk that credentials or derived secret material could be exposed through logs or saved files.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The template explicitly includes operational APIs to forbid or resume live streams, which can disrupt service availability, but it provides no warning, approval requirement, or guardrails around these disruptive actions. In a skill meant to manage production Alibaba Cloud Live resources, omission of cautionary notes and confirmation steps increases the chance of accidental or unauthorized denial of service against legitimate streams.

External Transmission

Medium
Category
Data Exfiltration
Content
output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
output_dir.mkdir(parents=True, exist_ok=True)

    url = (
        f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
        f"/versions/{args.version}/api-docs.json"
    )
    payload = fetch_json(url, timeout)
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.