ClawHub
Back to skill

Security audit

Giza

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Giza DeFi assistant for onboarding, portfolio review, withdrawals, rewards, and education, with sensitive actions scoped to Giza account workflows and confirmation steps for the highest-impact operations.

Install this only if you intend to use Giza for DeFi yield management. It can guide login and initiate account actions involving real stablecoin funds, so review network, token, protocol choices, amounts, and withdrawal/deactivation confirmations carefully; DeFi funds are not bank-insured and can be lost through smart-contract, stablecoin, or protocol risk.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
- **Withdrawals** (giza_withdraw): State the amount, destination, and that funds will leave the earning pool. Ask for "yes" to proceed.
- **Deactivation** (giza_deactivate_agent): Warn that the account will stop earning yield. Ask for "yes" to proceed.

After receiving confirmation, call giza_confirm_operation to finalize. Never auto-confirm any of these actions.

## Error Recovery

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation examples include very broad phrases such as "Get started" and "How does this work?" that can plausibly appear in ordinary conversation without the user explicitly intending to invoke a financial-management skill. In a high-risk DeFi context, accidental activation can lead to collection of account details, prompting for login, or steering the user into sensitive workflows that handle deposits, withdrawals, and protocol changes.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 396)May include surrounding context.

md
3. These platforms pay interest to borrowers, and you earn a share of that interest
4. The agent continuously monitors rates and moves your funds to wherever the best yield is -- automatically

You don't need to manage anything. Just deposit and let the agent work."

## What are the fees?

Static analysis

No suspicious patterns detected.