ClawHub
Back to skill

Security audit

Yield Offer Sanity Check

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only checklist for reviewing yield offers, with no evidence of hidden file access, persistence, or external execution.

This skill appears suitable as a lightweight checklist, but users should remember it does not independently verify platforms, audits, contracts, or on-chain data; treat its output as risk-screening guidance, not financial advice or a safety guarantee.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose describes a prompt-only checklist for assessing yield promotions. The supplied code chunk does not implement or evidence that behavior; instead, it tests security behavior of a handler when given a suspicious skill_name and verifies that local file reading does not occur. This is materially different from the declared purpose and indicates unrelated primary behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.