Back to skill

Security audit

fangcun-scam-radar

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rated this skill benign with medium confidence: it found no AIG alerts, but flagged a risk that its scenario mode may present assumed indicators as user-confirmed facts, and one referenced path was missing.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with the reported scenario-mode risk: illustrative assumptions may be presented as user-provided facts and could affect a scam-risk report. Confidence is medium, and inspection was marked partial because a referenced local path was missing; this leaves some evidence 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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

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

Scenario mode substitutes assumed risk indicators for user-provided facts.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

Scenario mode supplies unconfirmed indicators as true, then passes them through the same scoring and report generation used for user-confirmed facts. Although scenario names identify them as typical presets, the resulting report describes the indicators as facts supplied by the user and can issue strong risk warnings, creating a report-integrity problem in a financially sensitive context.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · tests/regen_snapshots.py (reported line 33)May include surrounding context.

python
def _run_case(script, args):
    return subprocess.run(
        [sys.executable, "-X", "utf8", str(script)] + args,
        capture_output=True, text=True, encoding="utf-8", errors="replace")