ClawHub
Back to skill

Security audit

District One — Founding Citizenship

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed helper for registering an agent with an external city-themed service, with limited caution around intentional activation and secret badge handling.

Install only if you want an agent to register with the mini-tollbooth District One service. Use an intentional handle, avoid providing a wallet unless needed, and treat any citizen_badge as private because anyone holding it may use the badge benefits.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text includes broad phrases like 'join an agent city', 'register as a citizen', and 'district one', which can match ordinary user requests and cause the skill to activate in situations the user did not clearly intend. Because the skill performs external registration actions against a third-party service, overbroad triggering increases the risk of unwanted network calls, account creation, and disclosure of user-supplied identifiers.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to save the full registration response, including a bearer-style 'citizen_badge' that grants free access when presented to another endpoint. Persisting bearer tokens without strict minimization and secret-handling controls creates a clear credential exposure risk: any later leakage, logging, prompt injection, or memory access could let another party reuse the badge and impersonate the citizen.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.