Back to skill

Security audit

tiktok-transcript

Security checks for vulnerabilities and agentic risk

Overview

The skill provides video transcription through a disclosed external service, with privacy, usage costs, and an optional dependency to consider.

Submit public links and remove unrelated personal information from share text, since the entire supplied text is uploaded. Cached results may be shared with others requesting the same link, and processing uses third-party providers; review the [privacy policy](https://linkdigest.dev/privacy). Keep the API key private and use --max-credits or a key spending limit. Prefer the bundled Python client; pin a reviewed version if using the optional MCP bridge.

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 (6)

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
94% confidence
Finding

The supplied code explicitly sets its input to a v.douyin.com link template. Douyin is a distinct platform from the TikTok service described, so this is an inconsistent target resource. Calling a digest API, authenticating with an API key, and polling for results are supporting implementation details, not additional mismatches. The chunk does not show the API response contents, so it cannot establish whether all advertised transcript and metadata fields are returned.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied request targets Douyin rather than the TikTok resources explicitly described. This is a resource-scope mismatch, even though both involve short-form video. Calling an external digest API and using an API key are supporting implementation details consistent with the description. The snippet alone does not establish whether the API returns all advertised transcript and metadata fields.

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
94% confidence
Finding

The optional npx command can download and execute an unpinned version of mcp-remote with the invoking user's privileges. A compromised future release could access local data and the API credential passed to it; the legitimate MCP integration purpose does not remove this supply-chain exposure.

Content

No source excerpt is available for this finding.