CTIPilot
AI-generated · no human review · verify critical claims against the linked source. how it works →

CERT-FR agentic-AI risk report (CERTFR-2026-ACT-016)

report · report:certfr-2026-act-016 single-source-national-cert

CERT-FR technical report on agentic AI tooling risks: prompt injection, MCP supply chain, and sandboxing guidance for organizations deploying AI coding agents (CERT-FR, May 2026).

Aliases: CERTFR-2026-ACT-016

Coverage
1
first 2026-05-08 → last 2026-10-21
Latest activity
2026-05-08
CERT-FR: keep autonomous AI assistants off workstations; use them only in isolated sandboxes holding no…
Peak priority
notable
1 notable
Targets
·
regions: europe
Sources cited
1
1 hosts

Defender insights

What each entry about CERT-FR agentic-AI risk report (CERTFR-2026-ACT-016) tells a defender to do, newest first.

2026-05-08NOTABLECERT-FR: keep autonomous AI assistants off workstations; use them only in isolated sandboxes holding no sensitive data

Exposure

Story timeline

  1. 2026-05-08CERTFR-2026-ACT-016: CERT-FR says autonomous AI assistants such as OpenClaw must not be deployed on workstations until proven secure
    active-threatsCERT-FR: keep autonomous AI assistants off workstations; use them only in isolated sandboxes holding no sensitive data

Hunting pivots

ATT&CK techniques (3 across 3 tactics)

3 techniques observed across 1 entry about this entity, derived from entry metadata and body evidence, never asserted without a published entry behind it · pinned to MITRE ATT&CK v20.1 · compare on the matrix · Navigator layer (JSON)

  • Initial AccessSupply Chain Compromise: Compromise Software Dependencies and Development Tools
  • ExecutionCommand and Scripting Interpreter
  • ExfiltrationExfiltration Over Web Service

Initial Access TA0001

T1195.001Supply Chain Compromise: Compromise Software Dependencies and Development Tools×1

Adversaries may manipulate software dependencies and development tools prior to receipt by a final consumer for the purpose of data or system compromise. Applications often depend on external software to function properly. Popular open source projects that are used as dependencies in many applications, such as pip and NPM packages, may be targeted as a means to add malicious code to users of the dependency. This may also include abandoned packages, which in some cases could be re-registered by threat actors after being removed by the original owner. Adversaries may also employ "typosquatting" or name-confusion by choosing names similar to existing popular libraries or packages in order to deceive a user.

Evidence: 2026-05-08/cert-fr-certfr-2026-act-016-agentic-ai-tools-introduce-promp · ATT&CK page ↗

Execution TA0002

T1059Command and Scripting Interpreter×1

Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries. These interfaces and languages provide ways of interacting with computer systems and are a common feature across many different platforms. Most systems come with some built-in command-line interface and scripting capabilities, for example, macOS and Linux distributions include some flavor of Unix Shell while Windows installations include the Windows Command Shell and PowerShell.

Evidence: 2026-05-08/cert-fr-certfr-2026-act-016-agentic-ai-tools-introduce-promp · ATT&CK page ↗

Exfiltration TA0010

T1567Exfiltration Over Web Service×1

Adversaries may use an existing, legitimate external Web service to exfiltrate data rather than their primary command and control channel. Popular Web services acting as an exfiltration mechanism may give a significant amount of cover due to the likelihood that hosts within a network are already communicating with them prior to compromise. Firewall rules may also already exist to permit traffic to these services.

Evidence: 2026-05-08/cert-fr-certfr-2026-act-016-agentic-ai-tools-introduce-promp · ATT&CK page ↗

Entries about CERT-FR agentic-AI risk report (CERTFR-2026-ACT-016) (1)

2026-05-08 · view entry permalink →

NOTABLEupdatedNATOA2

CERTFR-2026-ACT-016: CERT-FR says autonomous AI assistants such as OpenClaw must not be deployed on workstations until proven secure

CERT-FR's advisory CERTFR-2026-ACT-016, published on 2026-04-13, addresses autonomous personal assistants such as OpenClaw, Claude Cowork and open-source equivalents, whose adoption has grown strongly since early 2026. Unlike chat assistants, they execute commands, control the browser, read and write files, manage calendars and send mail, triggered by a text message through applications such as Slack, WhatsApp or Discord (CERT-FR, 2026-04-13). Plugins can be loaded dynamically and, depending on the integration model, run as trusted code with the application's privileges, which widens the software supply chain; prompt injection is an intrinsic weakness of the underlying language models, and an agent that orchestrates operating-system-level tools raises the risk of unauthorized command execution and data exfiltration through prompt injection or hijacked messages (CERT-FR, 2026-04-13). The advisory's risk list has five items: compromise of the user's workstation through a vulnerability in these tools, most of them still in beta; leakage of sensitive data by the agents to uncontrolled external resources; excessive access rights over all of the user's office applications (mail, calendar, file manager, business and HR applications); sharing of login credentials with the agents and their potential leakage; and loss of control over the agents' actions on the workstation, including destructive actions that damage the integrity or availability of business applications or data (CERT-FR, 2026-04-13).

CERT-FR's position is that such assistants must not be deployed on workstations and their use should be prohibited until the product is stabilised and proven from a security standpoint; they must in no case be deployed in production, only in isolated test sandboxes holding no sensitive data, and the same applies to mobile deployments (CERT-FR, 2026-04-13). Where they are used, the main lever is configuration hardening: limit the tools and actions available to the strict minimum, require human validation for any system command or action with side effects, run the agent in a sandbox, and allowlist the channels and interlocutors that may trigger it, for example only on an explicit mention of the agent (CERT-FR, 2026-04-13).

Correctionrun 2026-10-11T1307Z-audittitleheadlinesummaryevent_dateentitiestechniquessourcesclassificationbody

CERT-FR's advisory concerns autonomous personal assistants on workstations, not agentic orchestration platforms, and does not mention the Model Context Protocol; its supply-chain concern is plugins that load dynamically and run as trusted code (CERT-FR, 2026-04-13). Its recommendations are to keep these assistants off workstations and out of production, confine them to isolated sandboxes, restrict their tools, require human validation for system commands and allowlist the channels that may trigger them. The earlier text attributed guardrails, tool-call allowlisting and a rule to treat all agent output as untrusted to CERT-FR, and named products the advisory does not mention.

Improvementrun 2026-10-21T1149Z-auditsummarybodyheadline

CERT-FR's advisory lists five risks: compromise of the user's workstation through a vulnerability in these tools, most of them still in beta; leakage of sensitive data by the agents to uncontrolled external resources; excessive access rights over the user's office applications; sharing of login credentials with the agents and their potential leakage; and loss of control over the agents' actions, including destructive ones (CERT-FR, 2026-04-13).

threat08 May 05:00Zsingle-source · national CERTOpen finding →
Sources: CERT-FR

explore in graph

Where this entity is cited

  • Threats1

Source distribution

  • cert.ssi.gouv.fr1 (100%)