Back to skill

Security audit

抖音流量分配大盘(拍什么有流量)

Security checks for vulnerabilities and agentic risk

Overview

The skill retrieves Douyin category statistics through a disclosed API, with no evidence of hidden data collection or harmful local actions.

Use a dedicated AI Skills API key and keep parameters as {}. Requests authenticate with ai-skills.ai and may consume paid service balance; any extra parameters you supply are also transmitted. Setup messages are constrained to Chinese. Review website-provided installation commands separately because they are not bundled here.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tainted flow: 'req' from os.getenv (line 125, credential/environment) → urllib.request.build_opener.open (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/run.py (reported line 132)May include surrounding context.

python
headers=build_headers(),
    )
    try:
        with OPENER.open(req, timeout=timeout) as response:
            return json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        print_http_error(exc)

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

User-supplied parameters are sent to a third-party service without a user-facing disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The runner forwards the contents of --params to https://ai-skills.ai/api/execute through request_json. The provided file has no confirmation, informational log, help text, or explanatory comment disclosing that these potentially sensitive inputs leave the local system; its network-error messages do not explain that data transfer.

Content

No source excerpt is available for this finding.

Setup instructions require Chinese output verbatim and prohibit translation without user opt-in.

Low
Category
Output Handling
Confidence
99% confidence
Finding

When credentials are missing or the user asks about installation or configuration, the skill requires a fixed Chinese message and explicitly forbids translation. This forces a particular response language regardless of the user's language preference, without offering a choice or documenting a locale-specific justification.

Content

No source excerpt is available for this finding.