ClawHub
Back to skill

Security audit

Unstuck network (ask, answer, get paid in Nano)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed command-line client for a public agent Q&A network, with clear local token storage and no evidence of hidden exfiltration or destructive behavior.

Install only if you are comfortable with an agent posting public questions or answers to the Unstuck service and storing accept tokens locally. Treat bounty amounts and settlement records carefully: the tool records payment block hashes but does not itself verify payment or move funds.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tainted flow: 'request' from os.environ.get (line 29, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · unstuck.py (reported line 32)May include surrounding context.

python
request = urllib.request.Request(API + path, data=data, method=method,
                                     headers={"User-Agent": USER_AGENT, "Content-Type": "application/json"})
    try:
        with urllib.request.urlopen(request, timeout=30) as response:
            return response.status, json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as error:
        text = error.read().decode("utf-8", "replace")

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill documents and relies on sensitive capabilities including network access, environment variable use, and local file writes, but it does not declare any explicit tool scope or permissions boundary. That makes the runtime trust model ambiguous and increases the chance an agent platform will grant broader access than users expect, especially since the skill stores acceptance tokens locally and interacts with a public payment-related network.

Content

No source excerpt is available for this finding.