Back to skill

Security audit

抖音批量视频转文字 Douyin batch to text

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because the scanners report a mismatch between its promised speech-only default and behavior that may use higher-cost full extraction, alongside concerns about its declared purpose and capabilities.

Consider the verdict suspicious before installing. The main reported concern is that ordinary use may choose full extraction and incur higher service costs than the promised speech-only default; check that cost behavior and the skill's declared capabilities suit you. The scan is partial because some referenced local paths were not found in the supplied artifact, so the evidence does not cover those references.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Tainted flow: 'req' from os.environ.get (line 103, 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 111)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
98% confidence
Finding

The supplied code is a relevant supporting API client, but does not itself implement the declared batch-to-files workflow: there is no loop over links, account-video discovery, file-writing logic, or index assembly. Moreover, argparse defaults --depth to full and only sends an explicit depth for transcript or script, contrary to the declared speech-only default. Reading LINKDIGEST_API_KEY and contacting LinkDigest are consistent with the description, and the code does not request Douyin credentials or cookies. Other skill components could supply the missing orchestration, but none are present in the supplied chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The manifest promises speech-only extraction by default, but the batch CLI omits depth when no option is provided and documents that behavior as full extraction. Following the documented default invocation can therefore consume more paid credits than the user authorized, with the discrepancy amplified across a batch.

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.

The default extraction mode is full reading, contrary to the manifest's speech-only default.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The depth option defaults to None, so ordinary batch invocations send no depth and rely on the documented full-extraction service default. This contradicts the promised cheapest speech-only mode and can unexpectedly deplete the user's paid credits across multiple videos.

Content

No source excerpt is available for this finding.

Tainted flow: 'name' from os.environ.get (line 113, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/batch_export.py (reported line 114)May include surrounding context.

python
continue
        title = d.get("title") or (d.get("caption") or "").split("\n")[0][:40] or "(无标题)"
        name = f"{n:02d}-{safe_name(title)}.md"
        with open(os.path.join(args.out, name), "w", encoding="utf-8") as f:
            f.write(d.get("raw_markdown") or json.dumps(d, ensure_ascii=False, indent=2))
        likes = stat(d, "likes", "like")
        rows.append(f"| {n} | {title} | {d.get('author') or ''} | {d.get('posted_at') or ''} | {likes} | [{name}]({name}) |")

The CLI defaults to full extraction rather than the manifest's promised speech-only, lowest-cost mode.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

When invoked directly, this CLI defaults to full extraction and omits an explicit depth from the API request, rather than using the skill's promised speech-only default. That can cause unexpectedly higher credit consumption, although importing this module from the batch exporter does not execute this CLI default.

Content

No source excerpt is available for this finding.