ClawHub
Back to skill

Security audit

liquidation-pressure

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because it may allow a payment above its advertised price, though the scan does not indicate clear malicious intent.

Review the payment terms before installing. The scanner reports that an endpoint could request and receive an automatically signed $0.01 payment instead of the advertised $0.007, with repeated calls potentially adding up. The scan covered the single listed Markdown component completely; no clear malicious intent was reported.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Payment policy permits $0.01 per call despite the advertised universal $0.007 price.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

For USDC's six-decimal units, max_amount(10000) allows a $0.01 payment even though the skill promises every caller a $0.007 price until 2027-01-01. An endpoint requesting the higher amount could therefore obtain an automatically signed payment exceeding the advertised current price by $0.003 per call; repeated calls could accumulate excess charges. The explicitly documented standard-price ceiling suggests a configuration oversight rather than malicious intent, and limits the per-call exposure.

Content

No source excerpt is available for this finding.