Back to skill

Security audit

xiaohongshu-note-to-text

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a clearly disclosed link-to-text service, with ordinary privacy, usage-cost, and optional dependency considerations.

Submit public links and remove unrelated private text from pasted shares. LinkDigest uses external model providers and may share cached results with others requesting the same public link. Its [privacy policy](https://linkdigest.dev/privacy) also describes retained usage history. Set --max-credits to control spending, keep the API key out of conversations, and pin or skip 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
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
87% confidence
Finding

The core extraction workflow matches the description, including keyless summaries, authenticated results, consumer insights, and translation. The mismatch is limited to additional exposed capabilities: viral-content breakdown and broader platform coverage. API requests, job polling, environment-variable authentication, and output formatting are supporting implementation details, not mismatches. The supplied client delegates extraction and quotation verification to the remote service, so their accuracy cannot be established from this code alone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
实测同一条图文笔记(公开结果页:https://linkdigest.dev/d/5d0e7837ec2742ea4ae07806d979f0ce ):

- 直接 curl 网页,去掉脚本和样式后只剩 860 个可见字符;
- yt-dlp 报 `No video formats found`(它只认视频笔记);
- LinkDigest 返回的 Markdown 是 35,059 个字符,约为前者的 41 倍。

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
实测同一条图文笔记(公开结果页:https://linkdigest.dev/d/5d0e7837ec2742ea4ae07806d979f0ce ):

- 直接 curl 网页,去掉脚本和样式后只剩 860 个可见字符;
- yt-dlp 报 `No video formats found`(它只认视频笔记);
- LinkDigest 返回的 Markdown 是 35,059 个字符,约为前者的 41 倍。

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 76)May include surrounding context.

提交:

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://www.xiaohongshu.com/explore/<笔记ID>?xsec_token=<...>", "format": "json"}'

MCP server referenced without pinned version: 'npx mcp-remote'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

The optional stdio integration uses npx to fetch and execute mcp-remote without a pinned version, making executed code depend on the package version resolved at installation time. A compromised package release could execute with the user's local privileges and access the API key passed to the process; this is a supply-chain exposure, not evidence that the current package is malicious.

Content

No source excerpt is available for this finding.