视频转思维导图 Video to mind map (markmap)

• Outcome: Review
• Latest audit: Nov 12, 2026 · 12:29 AM UTC
• Version: 1.0.0

Overview

The scanners classify this video-to-mindmap skill as suspicious, mainly because its recommended install-related command can fetch an unpinned package and the reported implementation does not match the promised mind-map output.

Consider avoiding installation until the skill's behavior and tool scope are clarified and the rendering dependency is pinned to a reviewed version. The scan is partial: all three listed components were scanned, but a referenced local path was missing, so evidence about that reference is incomplete.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Taint Tracking: Direct Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (6)

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 network calls and API-key access are consistent with the declared LinkDigest integration, and the code does not directly log into platforms or download videos. However, the supplied chunk is a generic content-digestion client: it forwards requests and prints returned content without requesting or constructing the promised mind-map structure. Its additional translation and breakdown features and explicit Bilibili limitation further diverge from the description. Other skill components could potentially perform the missing transformation, but that behavior is not present in the supplied 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.

MCP server referenced without pinned version: 'npx markmap-cli'.

Medium

• Category: MCP Rug Pull
• Confidence: 96% confidence

Finding

The recommended unversioned npx command can download and execute a changing npm package with the invoking user's privileges. This introduces supply-chain exposure into an otherwise local conversion step; it is a CLI dependency, not an MCP server.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx markmap-cli'.

Medium

• Category: MCP Rug Pull
• Confidence: 95% confidence

Finding

The docstring recommends an unversioned npx invocation that can fetch and execute a changing npm dependency with local user privileges. The Python converter does not execute this command itself, but following the documented rendering step introduces supply-chain risk; this is not an MCP server reference.

Content

No source excerpt is available for this finding.

The client exposes paid viral-content analysis unrelated to video-to-mind-map conversion.

Low

• Category: Excessive Agency
• Confidence: 93% confidence

Finding

The --breakdown option (L268) enables “爆款拆解” (viral-content analysis), and L291–L292 forwards that request to the API. This is a separate, optionally charged capability (+1 credit according to L268), rather than the timestamped chapter and key-point extraction described by the manifest.

Content

No source excerpt is available for this finding.