Back to skill

Security audit

jd-data

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because generic product-analysis triggers may start a JD collection workflow outside its intended scope, and the skill does not declare its tool scope.

Consider installing only if you want JD collection and are comfortable reviewing requests that could trigger it from broader product-analysis prompts. The skill does not declare its tool scope, and the scan is partial because a referenced local path was missing; the evidence is therefore incomplete.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

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

Generic product-analysis and review-sorting triggers can activate the JD collection skill outside its intended scope.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The activation description explicitly includes generic product-data analysis, allowing requests unrelated to JD collection to select a paid external-service workflow. This can cause unnecessary authorization prompts or unintended point consumption when credentials already exist, although the JD-specific context and batch-budget checks reduce the risk.

Content

No source excerpt is available for this finding.

Tainted flow: 'CONFIG_PATH' from os.environ.get (line 38, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · jd_api.py (reported line 243)May include surrounding context.

python
"balance_points": balance_points,
        "saved_at": time.strftime("%Y-%m-%d %H:%M:%S"),
    }
    with open(CONFIG_PATH, "w", encoding="utf-8") as f:
        json.dump(payload, f, ensure_ascii=False, indent=2)
    try:
        os.chmod(CONFIG_PATH, 0o600)

Tainted flow: 'opts' from os.environ.get (line 354, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · jd_api.py (reported line 430)May include surrounding context.

python
text = json.dumps(body, ensure_ascii=False, indent=2)
        if opts["out"]:
            with open(opts["out"], "w", encoding="utf-8") as f:
                f.write(text)
            print(_summary(body, len(text.encode("utf-8"))) + f"\n已写入 {opts['out']}")
        else: