Reference

    Agentic AI Security Risks: Top Threats, Examples & Mitigations

    Last updated August 2026Reviewed by the Andeavour research team5 cited sources

    In short

    The main agentic AI security risks are prompt injection that turns data into commands, excessive agency from over-broad permissions, shadow agents nobody inventoried, memory and knowledge poisoning, tool and connector abuse, cascading failures across multi-agent systems, and compromise of the AI Principals that create and train agents — the failure mode with the largest blast radius.

    01

    Definition

    Agentic AI risk differs from classical application risk in three ways: the action path is chosen at runtime, the actor holds credentials of its own, and the population can grow without a human decision. Each property converts a familiar weakness into something faster and wider.

    OWASP's GenAI Security Project enumerates agent-specific threats including memory poisoning, tool misuse, privilege compromise, cascading hallucination and identity spoofing. MITRE ATLAS maps adversary techniques against AI systems observed in the wild. Both are useful checklists; neither replaces threat-modelling your own agents against your own data.

    Prioritize by reversibility and reach. A risk that produces a wrong answer is not equivalent to one that moves money, changes entitlements or reproduces itself.

    02

    Security risks

    1. Prompt injection, direct and indirect

    Untrusted content instructs the agent. With tools attached, the instruction becomes an action. Mitigate with trust separation, sanitization and hard capability limits.

    2. Excessive agency

    Permissions exceed the task because scoping is hard. Mitigate with task-derived, short-lived credentials and per-action authorization.

    3. Shadow agents

    Agents created in SaaS and developer tooling never enter inventory. Mitigate with continuous identity-side discovery and mandatory ownership.

    4. Memory and knowledge poisoning

    Writable memory and retrieval corpora persist manipulated content across sessions. Mitigate with write policy, provenance and quarantine.

    5. Tool and connector abuse

    Generic tools, unsigned manifests and unreviewed MCP servers expand reach silently. Mitigate with allow-lists, signing and parameter validation.

    6. Multi-agent cascades

    One agent's output is another's trusted input, so errors and injections propagate. Mitigate with inter-agent authentication and confidence-aware handoffs.

    7. Identity spoofing and impersonation

    Agents sharing service accounts make attribution impossible. Mitigate with one credential per agent and cryptographic workload identity.

    8. AI Principal compromise

    Compromising a creator or trainer mass-produces implanted agents. Mitigate with tier-0 treatment of the creation layer, signing and lineage revocation.

    9. Unbounded resource and cost abuse

    Loops and adversarial prompts drive token spend and API volume. Mitigate with quotas, circuit breakers and anomaly alerts.

    10. Insufficient traceability

    Without prompt, plan and tool-call records, incidents cannot be reconstructed. Mitigate with structured tracing and retention.

    03

    Examples

    Data exfiltration through a legitimate tool

    An agent uses its approved outbound email tool exactly as designed, on content chosen by an attacker's injected instruction.

    Entitlement escalation during routine work

    A DevOps agent adds a role to complete a task, and the role is never removed because no one reviews agent-made changes.

    Corpus poisoning at scale

    One manipulated internal page changes the answers of every retrieval-augmented agent in the company.

    Fleet-wide implant

    A compromised agent template silently adds an exfiltration step to every agent created after the change.

    04

    Architecture

    Attack surface inventory

    Enumerate inputs, tools, memory stores, credentials, models and creation paths for each agent class.

    Impact classification

    Score each possible action by reversibility, data sensitivity and financial exposure.

    Control mapping

    Map each risk to a specific enforcement point — identity issuance, tool broker, approval gate or monitoring rule.

    Detection coverage

    Define what abnormal looks like per agent: unusual tools, unusual data volumes, unusual creation rates.

    Response playbooks

    Pre-agreed procedures for revoking an agent, a Principal lineage or a model version.

    05

    Controls

    1

    Assume injection succeeds

    Design so that a successful injection still cannot perform an unacceptable action.

    2

    Cut standing privilege

    Short-lived, task-scoped credentials reduce the impact of nearly every risk in this list.

    3

    Gate by reversibility

    Autonomy for reversible actions, approval for irreversible ones, with the threshold documented and enforced in code.

    4

    Govern creation

    Rate-limit and authorize agent creation, sign templates, and prevent unbounded self-replication.

    5

    Trace everything

    Capture prompts, plans, tool calls and outcomes; without them, detection and forensics both fail.

    6

    Rehearse containment

    Test revoking an agent population end to end, and measure how long it actually takes.

    06

    Comparison

    Prioritizing risks by blast radius and reversibility.

    RiskBlast radiusReversible?Priority
    AI Principal compromiseEntire agent populationRarely, without lineage toolingCritical
    Excessive agencyAll systems in scopePartiallyCritical
    Indirect prompt injectionPer session, per agentUsuallyHigh
    Memory poisoningAll future sessionsWith provenance and rollbackHigh
    Shadow agentsUnknown by definitionAfter discoveryHigh
    Cost abuseBudgetYesMedium
    07

    Frequently asked questions

    Which risk causes most real incidents today?

    Excessive agency combined with untrusted input. Most damaging outcomes involve an authorized action taken for an attacker-chosen reason.

    Are multi-agent systems inherently riskier?

    They add propagation paths and reduce human checkpoints, so the same weakness reaches further and faster.

    How often should agent threat models be refreshed?

    On every change to tools, model version, data scope or creation path — these change the agent's capability more than code changes do.

    What is most commonly missed?

    The creation layer. Programs are creating agents faster than governance registers them, and few teams inventory those programs at all.

    08

    Sources

    1. [1]Agentic AI — Threats and MitigationsOWASP GenAI Security Project
    2. [2]OWASP Top 10 for LLM ApplicationsOWASP GenAI Security Project
    3. [3]ATLAS — Adversarial Threat Landscape for AI SystemsMITRE
    4. [4]AI Risk Management Framework (AI RMF 1.0)NIST
    5. [5]What is agentic AI security?Microsoft Security
    09

    How Andeavour addresses it

    Risk-ranked agent inventory

    AgentGuard scores each discovered agent by privilege, autonomy and data reach so remediation starts with the highest blast radius.

    Creation-layer defense

    Principals are monitored and their lineage recorded, addressing the risk most tooling omits entirely.

    External agentic attacks

    AgentHunter covers the inbound side: autonomous adversarial agents probing and abusing your applications.

    See it against your own environment

    A 30-minute technical session with the Andeavour team — no integration required to start.