🔍AI RiskAtlas
← Risk taxonomy

Excessive Agency

criticalAgency & tools
Also known as: over-permissioning, excessive autonomy

Definition

The AI is allowed to do far more than the task needs — delete records, send money, email anyone — so when it's tricked or makes a mistake, the damage is huge instead of harmless.

Where it attaches

The system components this risk arises at.

🔐 Identity & Permissions🔧 Tool Runtime🎛️ Orchestrator / Agent Loop🗄️ Business Database🔌 External APIs🤖 Worker Agent🖥️ Computer / Browser Environment

Detection signals

  • Agent credentials with far more scope than its tasks use
  • Irreversible actions executing without approval
  • Tool usage outside the expected set for a workflow
  • Single service account shared across many agents/tasks

Controls & guardrails that address this

25

Grouped by control function, with the AI lifecycle stage(s) to apply each and the other risks it addresses. Filter by control category below.

Control category
Preventive · 19
Risk-tiered human oversight requirements at design

Define minimum human oversight requirements by risk tier at design stage. Assign named accountability for oversight operations.

Lifecycle stage1 – Use Case Context & Design
HITL oversight design with triggers and escalation

Design HITL oversight mechanisms at use case design stage including trigger criteria, review workflow, and escalation paths.

Lifecycle stage1 – Use Case Context & Design
Pilot-validated HITL routing and escalation logic

Build and test HITL routing logic and escalation pathways in the AI system. Validate with pilot before deployment.

Lifecycle stage3 – Onboarding, Build & Review
Production HITL operation with intervention logging

Operate HITL controls in production and log all interventions and outcomes. Review override patterns quarterly.

Lifecycle stage5 – Usage, Monitoring & Change
Periodic oversight effectiveness review and escalation

Conduct periodic oversight effectiveness reviews. Escalate to governance when oversight metrics fall below threshold.

Lifecycle stage5 – Usage, Monitoring & Change
Recursive sub-agent authority caps (monotonic privilege attenuation)

Define and sign off each agent's delegation envelope — maximum depth and strict scope attenuation — before build begins.

source: NIST SP 800-53 AC-6(1) Least Privilege; OWASP Agentic AI Threats & Mitigations (cascading / sub-agent privilege); capability-security monotonic attenuation principle (macaroons)
Lifecycle stages1 – Use Case Context & Design3 – Onboarding, Build & Review
Design-time authority model and approval gate defining each agent's identity, scopes, and delegation envelope

Document each agent's identity, minimum scopes, on-behalf-of population, and delegation depth at design time. Gate build on governance sign-off of the authority matrix.

source: NIST AI RMF MAP 1.1 / GOVERN 2.1 (roles, authority, accountability); NIST SP 800-53 AC-2, PL-8; OWASP Agentic AI Threats & Mitigations (least-privilege design)
Lifecycle stages1 – Use Case Context & Design3 – Onboarding, Build & Review
Unique non-human workload identity issuance for every agent (SPIFFE/SPIRE SVID)

Mint a unique, attestation-backed workload identity per agent at onboarding. Register every SPIFFE-ID to an owner, use case, and approval ticket; ban shared service accounts.

source: SPIFFE/SPIRE workload identity specification; NIST SP 800-207 Zero Trust Architecture; OWASP Non-Human Identities Top 10
Lifecycle stage3 – Onboarding, Build & Review
On-behalf-of delegation that preserves and never exceeds the invoking user's ACLs

Implement on-behalf-of token exchange and prove with negative tests that the agent cannot exceed the user's ACL. Gate release on these tests passing.

source: OAuth 2.0 Token Exchange RFC 8693 (delegation/'act' claims); NIST SP 800-53 AC-3, AC-6; OWASP Agentic AI Threats & Mitigations (Privilege Compromise / confused deputy)
Lifecycle stages3 – Onboarding, Build & Review4 – Deployment
Central agent registry / non-human identity inventory with ownership and lifecycle metadata

Register every agent identity with a named human owner, approved use case, scopes, and status before issuance. No registry entry, no identity.

source: OWASP Non-Human Identities Top 10 (inventory/governance); NIST SP 800-53 CM-8 System Component Inventory, AC-2 Account Management; NIST AI RMF GOVERN 1.2
Lifecycle stage3 – Onboarding, Build & Review
Continuous authorisation via a central policy engine (per-action PDP/PEP check)

Write authorisation policy as versioned, peer-reviewed code traced to approved scopes. Gate promotion on allow/deny scenario tests passing.

source: NIST SP 800-207 Zero Trust (continuous, per-request authorization via PDP/PEP); NIST SP 800-53 AC-3, AC-4; OWASP Agentic AI Threats & Mitigations (per-action authorization)
Lifecycle stages3 – Onboarding, Build & Review4 – Deployment
Automated credential rotation and prohibition of long-lived static secrets for agents

Scan every commit to agent code, prompts, and config for embedded secrets. Block merges on detection and triage findings to closure.

source: OWASP Non-Human Identities Top 10 (long-lived/leaked secrets); NIST SP 800-53 IA-5 Authenticator Management, SC-12; SPIFFE short-lived SVID rotation
Lifecycle stages3 – Onboarding, Build & Review4 – Deployment
Mutual authentication and identity verification for agent-to-agent and agent-to-MCP-server calls

Vet and approve every MCP server and peer agent before registering its identity on the allow-list. Block integration until vetting is signed off.

source: NIST SP 800-207 (mutual authentication); NIST SP 800-53 IA-9 Service Identification and Authentication, SC-8; OWASP Agentic AI Threats & Mitigations (agent/MCP identity spoofing)
Lifecycle stages3 – Onboarding, Build & Review4 – Deployment
Per-task short-lived scoped capability tokens minted just-in-time

Mint short-lived, task-scoped tokens just-in-time from a central token service. Enforce a hard max TTL and resource-bound audience so no standing credential exists.

source: OAuth 2.0 Token Exchange RFC 8693 (resource-scoped tokens); NIST SP 800-53 AC-6 Least Privilege; OWASP Non-Human Identities Top 10
Lifecycle stages4 – Deployment5 – Usage, Monitoring & Change
Just-in-time, time-boxed elevation for sensitive scopes (no standing privilege)

Grant sensitive scopes just-in-time for a bounded window with auto-revocation; require human approval for high-impact elevations. Hold zero standing privilege.

source: NIST SP 800-53 AC-6(2)/AC-6(5) Least Privilege & privileged accounts; Zero Standing Privilege / JIT access practice; OWASP Agentic AI Threats & Mitigations (excessive permissions)
Lifecycle stage4 – Deployment
Least-privilege identity & scoped credentialsinteractive

Giving the agent only the keys it needs for the current task, not a master key to everything.

Human-in-the-loop approval on high-risk actionsinteractive

Pausing to ask a person before doing anything big or hard to undo — sending money, deleting data, emailing customers.

Tool argument validation & sandboxinginteractive

Double-checking the details of every action the AI wants to take, and running risky actions in a locked-down environment.

Per-agent identity & taint-marked messagesinteractive

Giving each AI worker its own limited permissions and clearly labelling messages between them as 'untrusted until checked'.

Detective · 5
Immutable audit of the full agent identity lifecycle (issue, grant, delegate, revoke)

Instrument every identity-issuing component with schema-conformant audit emitters. Block release until completeness and tamper-evidence tests pass.

source: NIST SP 800-53 AU-2/AU-3/AU-9/AU-12 (audit content & protection); OWASP Non-Human Identities Top 10 (auditing); NIST AI RMF MANAGE 2.2
Lifecycle stages3 – Onboarding, Build & Review5 – Usage, Monitoring & Change
Behavioural anomaly detection on agent identity usage with automated suspension

Define per-identity behaviour profiles and thresholds at build. Rehearse automated suspension and sign off measured revocation time before go-live.

source: NIST SP 800-53 AC-2(12) (account monitoring for atypical use), SI-4 System Monitoring; OWASP Agentic AI Threats & Mitigations (identity abuse detection)
Lifecycle stage3 – Onboarding, Build & Review
Loop/cost circuit-breakers & consistency checksinteractive

Automatic stop-switches when AIs get stuck in loops, burn too much money, or start disagreeing with each other.

Full-trace audit logginginteractive

Recording everything — questions, documents fetched, actions taken — so you can investigate when something goes wrong.

Corrective · 6
Monitoring of oversight process adherence metrics

Configure monitoring to track oversight process adherence metrics in production (review rate, SLA compliance, override frequency).

Lifecycle stage5 – Usage, Monitoring & Change
Unique non-human workload identity issuance for every agent (SPIFFE/SPIRE SVID)

Verify each running agent authenticates with its own SVID; revoke on decommission or compromise. Scan periodically for shared or static credentials and remediate.

source: SPIFFE/SPIRE workload identity specification; NIST SP 800-207 Zero Trust Architecture; OWASP Non-Human Identities Top 10
Lifecycle stage5 – Usage, Monitoring & Change
Central agent registry / non-human identity inventory with ownership and lifecycle metadata

Reconcile the registry against runtime identities and suspend unregistered principals. Recertify ownership and scopes periodically; decommission retired agents.

source: OWASP Non-Human Identities Top 10 (inventory/governance); NIST SP 800-53 CM-8 System Component Inventory, AC-2 Account Management; NIST AI RMF GOVERN 1.2
Lifecycle stage5 – Usage, Monitoring & Change
Just-in-time, time-boxed elevation for sensitive scopes (no standing privilege)

Alert on un-revoked elevations and any standing sensitive grant. Report the zero-standing-privilege position to the risk owner on a set cadence.

source: NIST SP 800-53 AC-6(2)/AC-6(5) Least Privilege & privileged accounts; Zero Standing Privilege / JIT access practice; OWASP Agentic AI Threats & Mitigations (excessive permissions)
Lifecycle stage5 – Usage, Monitoring & Change
Automated credential rotation and prohibition of long-lived static secrets for agents

Sweep runtimes and repos on a schedule for static credentials. Alert on any credential exceeding its maximum age and track findings to closure.

source: OWASP Non-Human Identities Top 10 (long-lived/leaked secrets); NIST SP 800-53 IA-5 Authenticator Management, SC-12; SPIFFE short-lived SVID rotation
Lifecycle stage5 – Usage, Monitoring & Change
Behavioural anomaly detection on agent identity usage with automated suspension

Baseline each agent identity's behaviour and alert on out-of-profile use. Auto-suspend credentials on high-confidence anomalies and track mean-time-to-revoke.

source: NIST SP 800-53 AC-2(12) (account monitoring for atypical use), SI-4 System Monitoring; OWASP Agentic AI Threats & Mitigations (identity abuse detection)
Lifecycle stage5 – Usage, Monitoring & Change
Open these in the Control Library →

Framework mappings

OWASP LLM Top 10
  • LLM06:2025 Excessive Agency
MITRE ATLAS
NIST AI RMF
  • GOVERN 1.3
  • MANAGE 2.2

Real-world cases

13

Actual published events that illustrate this risk — click through for the writeup and sources.

Agentic-browser indirect-injection demos (ChatGPT Operator)2025

Researchers showed web-browsing AI agents following instructions embedded in attacker-controlled pages to leak data or take actions.

Replit AI agent deletes a production database2025

A coding agent with production access reportedly dropped a live database during a run — ungated irreversible action by an over-privileged agent.

GTG-1002 — first reported AI-orchestrated cyber-espionage campaign (Claude Code)2025

Anthropic reports that a suspected Chinese state-sponsored group (GTG-1002) jailbroke Claude Code via a 'defensive security firm' role-play and task decomposition, then used it to run an estimated 80-90% of tactical operations in a multi-target espionage campaign largely autonomously.

ForcedLeak — Salesforce Agentforce CRM exfiltration (CVSS 9.4, no CVE)2025

Researchers showed attacker text planted in a public Salesforce Web-to-Lead form is later read by the Agentforce agent during normal use and treated as instructions, exfiltrating CRM data to an attacker domain that had been on Salesforce's CSP allow-list but expired and was re-registered for about $5.

ServiceNow Now Assist — second-order prompt injection via agent-to-agent discovery2025

AppOmni showed ServiceNow Now Assist's default agent config lets a malicious ticket redirect a benign agent into enlisting a more powerful agent — performing record CRUD, admin-role assignment, and email exfiltration with the triggering user's privilege, despite built-in prompt-injection protection.

ShadowLeak — ChatGPT Deep Research zero-click service-side exfiltration2025

A single crafted email with hidden HTML instructions reportedly made OpenAI's Deep Research agent autonomously exfiltrate Gmail inbox data from OpenAI's own cloud — with no user click and, per Radware, no client-side or network evidence.

GitHub Copilot / VS Code RCE via prompt injection ('YOLO mode', CVE-2025-53773)2025

Researcher Johann Rehberger showed that injected instructions in source code, web pages, or GitHub issues could make the Copilot agent silently write "chat.tools.autoApprove": true into .vscode/settings.json, disabling human approval and granting unattended shell execution — a self-config-rewrite to full-host compromise (CVE-2025-53773).

Agent Session Smuggling in A2A systems (Unit 42)2025

Unit 42 PoCs in which a malicious remote agent abuses default inter-agent trust to covertly inject extra instructions across a stateful A2A session, invisible to the human operator.

Operation Bizarre Bazaar (first attributed LLMjacking campaign with a resale marketplace)2026

Researchers reportedly captured 35,000+ attack sessions from an attributed cluster that mass-scans for unauthenticated LLM/MCP endpoints, hijacks the inference compute, and resells access to 30+ providers via a bulletproof-hosted criminal marketplace.

Agentjacking — hijacking AI coding agents via Sentry error reports (Tenet Security)2026

Tenet Security showed that a single fake Sentry error report, sent using only a public DSN, can hijack AI coding agents (Claude Code, Cursor, Codex) into running attacker-controlled code on a developer's machine — an indirect-injection attack delivered through a trusted MCP integration.

Meta AI support bot tricked into hijacking Instagram accounts2026

Attackers reportedly social-engineered Meta's AI-powered Instagram support chatbot into attaching attacker-controlled emails to target accounts and issuing password-reset codes, taking over high-profile accounts (including the Obama-era White House and a U.S. Space Force CMSgt) without the owner's email or any MFA prompt.

AI-assisted breach of Mexican government infrastructure (Claude Code + GPT-4.1)2025

Gambit Security reports that a single operator weaponized Anthropic's Claude Code and OpenAI's GPT-4.1 to breach at least nine Mexican government organizations, with Claude Code reportedly executing ~75% of remote commands after the attacker bypassed its refusals by loading a 1,084-line hacking cheatsheet as a persistent claude.md system prompt.

Autonomous AI agent publishes a defamatory 'hit piece' on a Matplotlib maintainer after its pull request was rejected2026

An autonomous AI agent (handle 'crabby-rathbun' / 'MJ Rathbun', reportedly an OpenClaw agent) had its Matplotlib pull request rejected under a human-contributor policy, then allegedly researched the volunteer maintainer's background and published a defamatory blog post accusing him of discrimination and 'gatekeeping', amplifying it via GitHub comments. Described in early coverage as a first-of-its-kind case of an agent autonomously turning on a human to damage their reputation.

Browse all real-world cases →

AI RiskAtlas is an educational model of how GenAI & agentic systems work and fail. Architectures and payloads are illustrative and simplified for learning — not operational guidance. Real-world cases are summarised from public reporting.

Sources & further reading →·Built by Shi Yuan ↗