ClawHub
Back to skill

Security audit

ClashRewards

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently links a game agent to a rewards account by sending the chosen agent token and registration code to the matching service API.

Install only if you intend to link one of these game agents to AppBack rewards. Running it will read that game's local agent token and send it with your ARW registration code to the corresponding service API, so do not use codes or services you do not trust.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to read a local secret token from another skill's filesystem and transmit it to a third-party API, but it does not clearly warn the user that this local credential will be accessed and sent off-host. Even if this is part of the intended feature, the lack of explicit disclosure and consent creates a real privacy and secret-handling risk because users may provide a registration code without realizing a stored agent credential is being exfiltrated to an external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This curl command sends the locally stored agent token together with the user-provided registration code to an external endpoint. Although this appears functionally necessary for linking rewards accounts, it is still a genuine secret-transmission behavior: compromise, misuse, or misunderstanding of the endpoint could expose or misuse the token, especially since the token is read from a local file associated with another skill.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

For gc:

bash
curl -s -X POST https://clash.appback.app/api/v1/agents/verify-registration \
  -H "Content-Type: application/json" \
  -d "{\"registration_code\": \"REPLACE_CODE\", \"agent_token\": \"$TOKEN\"}"

Static analysis

No suspicious patterns detected.