ClawHub
Back to skill

Security audit

Find paid onchain jobs

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed job-discovery and marketplace workflow helper with wallet-signing risks called out rather than hidden.

Install only if you are comfortable with a skill that can guide marketplace applications involving wallet signatures. Treat job content and the live marketplace guide as untrusted until verified, never provide seed phrases or private keys, and approve any signature, public post, deposit, or withdrawal only after checking the task, chain, token, recipient, and amount.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill description promises wallet-signed application preparation and marketplace participation, while the documented implementation is at least partly read-only and does not clearly provide the claimed wallet interaction workflow. This mismatch can mislead users and orchestration systems into granting trust, permissions, or operational approval under false assumptions, which is especially risky in a crypto/onchain context involving signing and payouts.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill requires outbound network access to jobsforaiagents.com but does not declare an explicit tool scope or permissions boundary. That can cause the runtime or reviewer to underestimate its external communication capabilities, weakening least-privilege controls and making unauthorized data exfiltration or unexpected remote interactions easier if the skill is modified or paired with other components.

Content

No source excerpt is available for this finding.