ClawHub
Back to skill

Security audit

CostLens

Security checks for vulnerabilities and agentic risk

Overview

CostLens is a straightforward offline cost-reporting skill that reads user-selected JSON event logs and optionally writes a user-selected report file.

Before installing, understand that CostLens will read the event log path you provide and that report mode can create or overwrite the output file path you provide. Avoid pointing it at sensitive logs unless you are comfortable having their aggregate cost data included in local output.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
This markdown file is written entirely in Simplified Chinese, which can be interpreted as a language-specific presentation constraint. Although alternate language links are provided, the file itself does not ask for user language preference or explicitly frame the locale as optional within the content.

Missing User Warnings

Low
Confidence
76% confidence
Finding
The report command creates directories and writes a JSON report to the path supplied by --out. While this behavior is part of the command's functionality, the code path itself has no confirmation prompt or explicit disclosure at the point of write other than the help text showing an output path argument.

Static analysis

No suspicious patterns detected.