Back to skill

Security audit

douyin-video-to-text

Security checks for vulnerabilities and agentic risk

Overview

The skill performs its disclosed video-to-text task through LinkDigest, with clear privacy and spending considerations and an optional dependency risk.

Submit only public links and share text you are comfortable sending to LinkDigest. Its [privacy policy](https://linkdigest.dev/privacy) describes third-party processing, retained usage history, and shared cached digests. Protect your API key and use --max-credits or a key spending limit. Prefer the bundled Python client or native HTTP integration; review and pin mcp-remote if you choose that optional bridge. Backend privacy claims cannot be verified from the client code.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Tainted flow: 'req' from os.environ.get (line 102, credential/environment) → urllib.request.urlopen (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/linkdigest.py (reported line 110)May include surrounding context.

python
if data is not None:
        req.add_header("Content-Type", "application/json")
    try:
        with urllib.request.urlopen(req, timeout=timeout, context=_SSL["context"]) as resp:
            status, headers, raw = resp.status, resp.headers, resp.read()
    except urllib.error.HTTPError as err:
        status, headers, raw = err.code, err.headers, err.read()

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The core API submission, authentication, polling, and output behavior supports the declared Douyin extraction purpose. However, the code exposes additional paid translation and content-analysis capabilities not disclosed in the description, and advertises a wider platform scope. These are functional extensions rather than merely supporting implementation details. No unrelated local-file collection, Douyin credential access, or local video downloading is evident. Extraction quality, backend download behavior, and actual pricing cannot be verified from this client code.

Content

No source excerpt is available for this finding.

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

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
60% 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 · SKILL.md (reported line 70)May include surrounding context.

直接调 HTTP(没有 Python 时)

bash
curl -sS -X POST https://linkdigest.dev/api/v1/digest \
  -H "Authorization: Bearer $LINKDIGEST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://v.douyin.com/<短链>/", "format": "json"}'

MCP server referenced without pinned version: 'npx mcp-remote'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The optional stdio integration recommends executing an unpinned npm package through npx, allowing the resolved package version to change without review. A compromised release or dependency could execute with the user's local privileges and access the API credential supplied to the bridge; this risk is limited to users who choose this integration path.

Content

No source excerpt is available for this finding.