Security audit

AAP Agent Bounty

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is clear about verifying proofs and optionally submitting a user-confirmed 0 ETH Base transaction.

Before installing, be comfortable with the skill using your local GitHub auth or optional GH_TOKEN and your user-managed cast signer context. Review the exact transaction command, confirm the target wallet and 0 ETH value, and only set confirm_broadcast: true if you accept public on-chain proof data and any Base gas cost.

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)

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The package metadata describes this as an "Instruction-only skill package metadata," which does not match the provided manifest context describing a verification-first helper with optional 0 ETH Base claim submission. This is a semantic mismatch in declared purpose that could mislead reviewers about what the skill is intended to do.

Static analysis

No suspicious patterns detected.