UTC

OWASP Top 10 for LLM Applications 2026

LLM03:2026 Excessive Agency

8 advisories on ShieldMap fall under it through CWE-732, and 3 technique pages explain how the attacks work.

OWASP Top 10 for Agentic Applications
  • ●ASI01:2026 Agent Goal HijackPrompt injection or hallucination diverting an agent from its intended task is the trigger mechanism for Excessive Agency ("hallucination/confabulation... or direct/indirect prompt injection")
  • ●ASI02:2026 Tool Misuse & ExploitationA manifestation of Excessive Agency, where extensions/tools carry functionality beyond what the task needs
  • ●ASI03:2026 Identity & Privilege AbuseA manifestation of Excessive Agency, where extensions connect with generic, over-privileged identities
  • ●ASI05:2026 Unexpected Code Execution (RCE)A shell-command extension that fails to filter out unintended commands, and a coding agent whose excessive autonomy and permissions destroyed production infrastructure
  • ●ASI07:2026 Insecure Inter-Agent CommunicationA malicious/compromised peer agent in multi-agent/collaborative systems is a trigger, and user authorization scope must be preserved "across chained extension or agent calls"
  • ●ASI08:2026 Cascading FailuresA manifestation of Excessive Agency, countered by rate limiting and circuit breakers to halt runaway extension invocation
  • ●ASI09:2026 Human-Agent Trust ExploitationExcessive autonomy (failing to seek confirmation before high-impact actions) and human-in-the-loop approval both concern trust placed in unsupervised agent action
CWE weaknesses
  • ●CWE-285 Improper AuthorizationAuthorization must be enforced at a policy decision point in application logic rather than left to the model, defending against confused-deputy and privilege-abuse behavior.
  • ●CWE-732 Incorrect Permission Assignment for Critical ResourceDatabase identities and service accounts granted write and delete rights or broadly high privileges beyond what the task needs are a named root cause of excessive agency.
  • ○CWE-284 Improper Access ControlThe pillar umbrella covers the entry's permission and access-control failures, including missing mediation and lost user context.
  • ○CWE-770 Allocation of Resources Without Limits or ThrottlingThresholds and circuit breakers on invocation count or cumulative parameter value are needed to halt runaway tool calls.
  • ○CWE-1427 Improper Neutralization of Input Used for LLM PromptingDirect and indirect prompt injection, such as a crafted email, is the trigger that turns excess permissions into harmful action.
MITRE ATLAS tactics
  • ●AML.TA0005 ExecutionAn over-broad extension, such as one that runs unfiltered shell commands, lets the agent execute damaging operations, including destructive commands against production systems.
  • ●AML.TA0011 ImpactExcessive permissions turn an agent action into confidentiality, integrity, and availability harm, from deleting a user's email to destroying production databases and their snapshots.
  • ○AML.TA0010 ExfiltrationAn indirect injection can make an over-permissioned mail extension forward sensitive inbox contents to an attacker-controlled address.
  • ○AML.TA0012 Privilege EscalationA confused-deputy or weaponized over-privileged agent lets an attacker act with the agent's standing high privileges.
NIST AI 600-1 risks
  • ●NIST Information SecurityExcessive agency lets an agent exfiltrate data, perform unauthorized writes, and take destructive actions across the downstream systems it can reach.
  • ○NIST Human-AI ConfigurationExcessive autonomy acting without confirmation is a root cause, and human-in-the-loop approval is the primary control, both configuration of human oversight.
  • ○NIST ConfabulationHallucinated or confabulated reasoning can trigger the agent to take damaging real-world actions.
  • ○NIST Data PrivacyAn over-privileged agent can forward a user's private email content to an attacker, a personal-data breach.
NIST AI RMF categories
  • ○MANAGE 4 risk treatment, response & recoveryLogging and monitoring of extension and downstream activity is paired with circuit breakers that halt, rate-limit, or escalate agent actions for human review.
OWASP GenAI Data Security
  • ●DSGAI02 Agent Identity & Credential ExposureExtensions granted broad write access or a shared high-privilege account let a hijacked agent act far beyond its intended scope, so binding actions to user-scoped credentials across chained calls is the core control.
  • ●DSGAI06 Tool, Plugin & Agent Data Exchange RisksThe whole risk concerns extensions, tools, and plugins that retain unneeded capabilities an attacker can trigger, such as a mail extension that keeps its send function.
  • ○DSGAI01 Sensitive Data LeakageExcess agency lets a compromised agent scan a mailbox for sensitive information and forward it to an attacker.
OWASP AIVSS agentic risks
  • ●AIVSS-1 Agentic AI Tool MisuseExtensions carry functions beyond what the task needs, such as read-only access bundled with modify, delete, or send, so a malfunctioning model invokes capabilities it was never meant to use.
  • ●AIVSS-2 Agent Access Control ViolationExtensions connect to downstream systems with over-broad or generic high-privileged identities, letting the agent act far beyond the user's own authorization scope.
  • ●AIVSS-7 Insecure Agent Critical Systems InteractionAn open-ended shell-command extension that fails to filter unintended commands, or an over-autonomous coding agent, can execute damaging actions and destroy production infrastructure.
  • ○AIVSS-3 Agent Cascading FailuresWithout rate limits or circuit breakers, runaway extension invocation compounds into cascading downstream failures.
  • ○AIVSS-4 Agent Orchestration and Multi-Agent ExploitationA malicious or compromised peer agent can trigger damaging actions, and failing to preserve user context across chained agent calls widens the blast radius.
  • ○AIVSS-10 Agent Goal and Instruction ManipulationDirect or indirect prompt injection, such as a crafted incoming email, is the trigger that redirects the agent into unwanted privileged actions.
CSA AI Controls Matrix domains
  • ●IAM Identity & Access Management
  • ○AIS Application & Interface Security
  • ○LOG Logging and Monitoring
  • ○TVM Threat & Vulnerability Management

Mappings and their reasons from the OWASP Top 10 for LLM Applications 2026, Appendix A (OWASP GenAI Security Project), shared under CC BY-SA 4.0. Mappings restructured as data; the ATT&CK section and the AICM relevance text left out. Navigation, not a compliance claim.