Back to skill

Security audit

linkdigest-video-transcript

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its video-transcription purpose, with disclosed cloud processing, usage charges, and privacy tradeoffs.

Submit only public links and share text you are comfortable sharing with LinkDigest; keyless use still sends them. Set --max-credits to limit charges. Prefer the bundled script or direct HTTP integration, or pin a reviewed mcp-remote version. Review the [privacy policy](https://linkdigest.dev/privacy), which describes retained link history and shared digest caching.

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
97% confidence
Finding

The core API submission, polling, and output behavior matches the declared extraction workflow. However, the platform-support contradiction and additional paid processing options make the description incomplete or inaccurate. The keyless summary path is another concrete discrepancy. No unrelated data collection or malicious behavior is evident in the supplied code; API-side extraction quality, platform coverage, and actual billing cannot be independently verified from this client.

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 integration command uses npx to execute mcp-remote without selecting a reviewed version, allowing package resolution to introduce changed executable code. A compromised release could run with the client's local privileges and access credentials available to that process; this risk is conditional on using the optional integration.

Content

No source excerpt is available for this finding.

Despite the manifest requiring LINKDIGEST_API_KEY, the script automatically submits user content without a key.

Low
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest states that LINKDIGEST_API_KEY is required, but L306–L307 invoke free_look when it is absent. That function posts the supplied link or share text to the API without authentication (L142), returning a limited summary rather than the advertised full transcript and on-screen text. Missing credentials therefore do not prevent external submission as the stated prerequisite suggests.

Content

No source excerpt is available for this finding.