ClawHub
Back to skill

Security audit

B站视频转文字 Bilibili video to text

Security checks for vulnerabilities and agentic risk

Overview

The skill uses LinkDigest for the requested transcription task, with ordinary API authentication and outdated Bilibili error wording.

Use a dedicated API key with a credit cap and set --max-credits when controlling spending. Submit public URLs and remove sensitive text from share messages because the entire supplied message is forwarded. The provider's [privacy policy](https://linkdigest.dev/privacy) describes usage-history retention, third-party processing, and shared caching of public-link digests. Bilibili error wording in this client may be outdated.

A.I.G

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

SkillSpector

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 (4)

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
99% confidence
Finding

The strongest mismatch is the advertised Bilibili functionality: fail() handles HTTP 422 by printing '平台不支持（B站不支持）', and the CLI description instead advertises Xiaohongshu, Douyin, TikTok, YouTube, X, and WeChat articles. The script only delegates processing to the remote API, so the supplied code cannot establish the backend's current support or billing guarantees; nevertheless, its explicit unsupported-platform message directly contradicts the declared primary purpose. The code does not itself log into Bilibili, use Bilibili cookies, or download video, so those restrictions are consistent.

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 Bilibili transcription skill uses a client that explicitly identifies Bilibili as unsupported.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest specifically promises transcription and extraction for bilibili.com/video/BV… and b23.tv links, but L207 explicitly tells users that Bilibili is unsupported. The CLI description at L264 instead advertises other platforms, reinforcing that this client does not match the skill's central advertised purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.