ClawHub
Back to skill

Security audit

xiaohongshu-search-to-text

Security checks for vulnerabilities and agentic risk

Overview

The skill searches and reads public Xiaohongshu notes through LinkDigest, with disclosed data sharing, credit costs, and user control over which notes are read.

LinkDigest receives your search terms and supplied links or share text, and requests can spend credits. Choose which notes to read and consider the available per-read credit cap or API-key quota. Provider-side deletion and retention claims cannot be verified from these local files.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (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
98% confidence
Finding

The reading portion is consistent with the description: the script sends supplied content to LinkDigest and returns the service's digest, without requesting Xiaohongshu cookies or login. However, the declared primary entry point—searching notes by topic—is not implemented in this chunk; input is submitted only as a URL/share-text field to /api/v1/digest. The code also exposes translation, analysis, and video-transcript options beyond the declared functionality. Reading LINKDIGEST_API_KEY, making API requests, and polling jobs are expected supporting implementation details, not suspicious resource access. The supplied code does not show unrelated file collection or local file writes.

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 client exposes cross-platform video processing beyond the Xiaohongshu note-search-and-reading purpose.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The manifest describes searching Xiaohongshu and reading selected notes, but the CLI explicitly supports Douyin, TikTok, YouTube, X, and WeChat links (L264) and offers credit-consuming long-video transcription controls (L270-L272). These are operational capabilities rather than documentation alone: arbitrary supplied text becomes the request's URL field (L289), the video-processing options are added to the body (L302-L305), and the request is submitted using the configured API key (L310).

Content

No source excerpt is available for this finding.