ClawHub
Back to skill

Security audit

anti-cheat-identity

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small local decision-support tool for contest anti-cheat checks, with no evidence of hidden execution, persistence, data exfiltration, or direct enforcement actions.

Install only if you are comfortable giving the tool contest author IDs and environment fingerprint hashes. Treat its risk labels as triage advice, not proof of cheating or an automatic basis for penalties; a human organizer should review any warning before action is taken.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The user-facing content is entirely in Chinese, including the title, usage guidance, warnings, FAQ, and surrounding documentation. Under the policy provided, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified; this file does not clearly state that the skill is Chinese-only or region-specific.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The module docstring and all user-facing descriptions are written only in Chinese, and the CLI help/output strings likewise assume Chinese as the required language. There is no indication of language choice, opt-in, or documented justification for restricting the skill to a single locale.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Content
out_list.append({"tool": META["slug"], "input": d, "errors": [str(e)], "rc": 2, "aigc_mark": AIGC})
        print(json.dumps(out_list, ensure_ascii=False, indent=2))
        sys.exit(0 if allok else 2)
    args = {k: getattr(ns, k) for k in argnames}
    try:
        res, rc = _run(args)
    except GateError as e:
Confidence
50% confidence
Finding
Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Static analysis

No suspicious patterns detected.