ClawHub
Back to skill

Security audit

Pre judgment of similar cases wdy

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent legal-retrieval helper, but it can send sensitive dispute details to a third-party API without a firm approval or redaction step.

Review before installing if you may describe real legal disputes. Use only minimized, redacted queries, avoid names, IDs, addresses, account details, exact private facts, or legal strategy, and understand that queries are sent to Wendaoyun's external API using your API key.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:25
Finding

Unredacted Legal-Case Information May Be Transmitted to a Third-Party API Without Explicit Consent

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill’s trigger terms are broad enough to match ordinary discussion about disputes, debt, fraud, contracts, or lawsuits, which can cause the skill to activate when the user did not explicitly ask for legal retrieval. In this skill, unintended activation matters because it can lead to sending sensitive case narratives to a third-party API, creating unnecessary privacy and consent risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill explicitly instructs transmitting user-provided case descriptions to an external service using an API key in an authenticated request. Because legal disputes often contain highly sensitive personal, financial, and factual details, this external transmission creates a real confidentiality and privacy risk, especially where users may not understand that their data is being sent off-platform.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

调用示例：

bash
curl -s -X POST "https://h5.wintaocloud.com/prod-api/api/invoke/get-laws" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${WENDAOYUN_API_KEY}" \
  -d '{"content": "合同违约赔偿", "top_k": 3}'

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation logic says to directly retrieve whenever legal keywords appear, without clear boundaries for ambiguity, consent, or sensitivity screening. In context, this increases the chance of automatic external lookup based on partial or casual mentions of legal topics, again exposing potentially sensitive facts to the third-party service without sufficient user confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.