OWASP Agentic
ASI02 · Tool Misuse and Exploitation
Legitimate tools are used in unsafe or unauthorised ways: destructive commands, data exfiltration, chained calls.
OWASP Top 10 for Agentic Applications (2026)
Mitigations
- Narrow tool scopes and arguments
- Policy enforcement on tool calls
- Approval gates for destructive actions
Detections 8
- AI coding agent CLI started with an approval-bypass flag
- AI CLI run non-interactively with a bypass flag by a script interpreter (s1ngularity pattern)
- Command spawned by an AI coding agent references credential files
- Destructive cloud or cluster CLI command launched under an AI coding agent
- s1ngularity (Nx) artifacts: AI CLI bypass runs in shell history and /tmp/inventory.txt
- Claude Code telemetry: Bash tool commands that read credential stores
- Claude Code telemetry: sessions running in bypassPermissions mode
- MCP server process started by an AI client connects to a rare internet destination
Related techniques
- LLM06 Excessive Agency OWASP LLM
- AML.T0053 AI Agent Tool Invocation MITRE ATLAS
- AML.T0101 Data Destruction via AI Agent Tool Invocation MITRE ATLAS
In the news
-
Signal blocks screenshots on iOS 27 and Android to stop AI agents from reading private chats
Signal is blocking screenshots on iOS 27 and Android to keep AI agents such as Siri AI, Gemini Intelligence and Meta's Muse from reading private chats; protections remain incomplete on macOS.
MitigateEnable Signal's screenshot blocking and note macOS protections remain incomplete
-
MCP server Flyto Core: Flyto2 Core: SSRF guard bypass via DNS rebinding (validate_url_ssrf resolves-then-connects without pinning)
GHSA-6pm8-6f34-9v3g: Flyto Core MCP server's SSRF guard can be bypassed via DNS rebinding because it resolves then connects without pinning.
PatchUpgrade flyto-core to 2.26.8 or later
-
MCP server io.github.es617/obsidian-sync-mcp: obsidian-sync-mcp: Missing Host/Origin validation lets a public website drive a victim's Obsidian vault via DNS rebinding (no-auth mode)
Missing Host/Origin validation in obsidian-sync-mcp (npm, before 0.5.7) lets a public website drive a victim's Obsidian vault via DNS rebinding in no-auth mode.
PatchUpgrade obsidian-sync-mcp to 0.5.7 or later
-
Tether: Verified Stateful Policy Engine for System-Level Monitoring of Agents
Tether is a verified stateful policy engine that enforces security policies on the observed side-effects of AI agents executing shell commands and programs.
-
ToolPulse: Side-Channel Eavesdropping on Tool-Using LLM Agents
ToolPulse shows a side-channel attack can eavesdrop on tool-using LLM agents by exploiting local tool execution and shared system libraries on the user's machine.
ReviewReview exposure of local tool execution on agent-connected user machines
-
MCP server io.github.ConnorBritain/mssql-writer: mssql-mcp-core: SQL injection in mssql-mcp write tools via unparameterized table names and WHERE clauses
SQL injection in the write tools of the mssql-mcp-writer MCP server (npm, before 0.5.0) via unparameterized table names and WHERE clauses (GHSA-2m9m-6cr5-9x25).
PatchUpgrade @connorbritain/mssql-mcp-writer to 0.5.0 or later
-
Intent Contracts: Taking Tools Away from Agents
Researchers introduce intent contracts, an authorization interface that removes tools from the planning model in tool-using LLM agents and routes calls through a trusted model.
ReviewReview tool authorization for LLM agents against planner-driven command risks
-
When Do Decision Models Help LLM-Driven Network Discovery?
A simulation study finds that validating LLM-generated network discovery commands with decision models affects open-port recovery in penetration tests at various network scales.
-
Siemens Mendix Studio Pro
Siemens Mendix Studio Pro MCP Server has flaws enabling unauthorized remote tool execution and CSRF (CVE-2026-112136, CVE-2026-112137).
PatchUpdate Mendix Studio Pro 11 to 11.16.0 or 11.12 to 11.12.7
-
Can You Undo It? Reversibility Classes for AI Agent Actions
Paper proposes Reversibility Classes, a five-level vocabulary for whether AI agent tool actions can be undone, covering 536 tools across 20 MCP servers.
ReviewReview agent tool permissions for actions that cannot be reversed
Tools
Detect or mitigate it
- Agentic Radar Agent & MCP security · Hold
- clawsec Agent & MCP security · Assess
- Mastyf Agent & MCP security · Assess
- nono Agent & MCP security · Assess
CVEs
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.