ClawHub
Back to skill

Security audit

店店通·商场数据与洞察

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign with medium confidence: its reported mall-data query behavior appears purpose-aligned, though one referenced output file was not available for analysis.

The verdict is benign, not a guarantee of safety. Consider whether you are comfortable providing an API key through an environment variable and whether the skill's Chinese-language instruction suits you. Analysis was partial: all three listed components were scanned, but a referenced output file was missing, so evidence about that file is incomplete.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tainted flow: 'request' from os.environ.get (line 40, credential/environment) → urllib.request.build_opener.open (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/mall_query.py (reported line 42)May include surrounding context.

python
params = {"q":args.name,"city":args.city} if args.command=="search" else {"mall_id":args.mall_id,"radius_m":args.radius}
    request = urllib.request.Request(BASE+"/"+args.command+"?"+urllib.parse.urlencode(params),headers={"Authorization":"Bearer "+key,"Accept":"application/json"})
    try:
        with urllib.request.build_opener(NoRedirect).open(request,timeout=120) as response:
            raw=response.read()
            payload=json.loads(raw)
    except urllib.error.HTTPError as exc:

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

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 skill requires field explanations in Chinese without user opt-in.

Low
Category
Output Handling
Confidence
98% confidence
Finding

The instruction “中文解释字段” explicitly requires explanations of fields in Chinese. It does not offer a language choice or justify why Chinese is required, so it could override the user's preferred language.

Content

No source excerpt is available for this finding.