ClawHub
Back to skill

Security audit

appliance-energy-audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local appliance energy calculator, and the files I inspected do not show hidden network access, persistence, credential handling, or unrelated behavior.

Install only if you are comfortable running a local Python script on appliance inventory data you provide. Keep inventory JSON files limited to appliance details and utility usage numbers; there is no need to include secrets, account credentials, or unrelated personal files.

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
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises shell and file-reading usage through its documented commands, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap: an agent runtime may permit broader tool access than intended, making it easier for the skill to read local files or invoke shell commands outside the narrow energy-audit workflow. In this context the commands look functional rather than overtly malicious, but undeclared capabilities still increase attack surface.

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 · scripts/test_energy_audit.py (reported line 18)May include surrounding context.

python
def run_cli(args):
    return subprocess.run([sys.executable, ENGINE] + args,
                          capture_output=True, text=True)