Resources/AI Findings

AI Audit Findings Library

Reusable finding patterns for real AI security work. Each entry focuses on the root cause, exploit path, evidence an auditor should collect, and what to check next.

Approval Scope Mismatch on High-Impact Actions

Critical

The operator approves a coarse action label, but the agent retains control over the risky parameters that determine the true impact.

Human Approval BypassTool Misuse

Affected systems: Coding agents, Long-lived agents, Agentic DeFi systems

Persistent Memory Poisoning with Temporal Re-Entry

Critical

A low-trust write enters durable memory or summary state and is later retrieved in a higher-trust context that unlocks privileged action.

Memory PoisoningIndirect Prompt Injection

Affected systems: Long-lived agents, Multi-agent orchestration systems, Agentic DeFi systems

Prompt-to-Shell Execution via Unsafe Command Construction

Critical

Untrusted prompt-derived content reaches shell execution through string interpolation, template expansion, or unsafe command wrappers.

Indirect Prompt InjectionTool MisuseCapability Escalation

Affected systems: Coding agents, MCP-connected agents, Long-lived agents

Tool or Manifest Capability Overclaim

High

A tool, plugin, skill, or MCP manifest overstates its safety or understates the authority it actually grants to the agent runtime.

Skill, Plugin, and Integration BackdoorsTool Misuse

Affected systems: MCP deployments, Coding agents, Long-lived agents

Unverified Financial Destination Selection

Critical

The agent selects recipients, routers, bridges, protocols, or calldata destinations from mixed-trust context without independent validation.

Agentic DeFi Execution RiskTool Misuse

Affected systems: Agentic DeFi systems, Treasury agents, Trading agents

Smart Contract Security Digest

Monthly exploit breakdowns, audit checklists, and DeFi security research — straight to your inbox

© 2026 Zealynx