OWASP Agentic
ASI04 · Agentic Supply Chain Vulnerabilities
Malicious or compromised MCP servers, skills, plugins, prompts or models enter the agent's runtime.
OWASP Top 10 for Agentic Applications (2026)
Mitigations
- Allowlist MCP servers and skills
- Pin and review tool descriptions
- Scan third-party agent components
Detections 8
- YARA: s1ngularity (Nx) telemetry.js payload and shell-profile shutdown line
- Claude Code / VS Code project persistence files from the Mini Shai-Hulud worm
- YARA: SANDWORM_MODE npm worm and its McpInject rogue MCP server
- AI tool MCP or agent configuration written by a process other than the tool
- AI tool MCP configuration file modified by an unexpected process (Sigma, macOS/Linux)
- New MCP server registered through an agent CLI (claude / codex / gemini mcp add)
- YARA: MCP or hook config that launches a script from a hidden home directory or pipes curl into a shell
- MCP server process started by an AI client connects to a rare internet destination
Related techniques
- LLM03 Supply Chain OWASP LLM
- AML.T0010 Supply Chain Compromise MITRE ATLAS
- AML.T0110 AI Agent Tool Poisoning MITRE ATLAS
In the news
-
Microsoft agent-framework Compromised: Credential Stealer Targets Azure and CI Pipelines
Versions 1.26.1 and 1.26.2 of Microsoft's agent-framework PyPI package were published with a credential stealer targeting Azure and CI pipelines; they were quarantined.
HuntHunt for agent-framework 1.26.1/1.26.2 installs in CI pipelines and rotate exposed Azure credentials
-
Cursor Supply Chain Attack Started at Fireworks AI
Attacker stole an access key from Fireworks AI and used it to exfiltrate credentials, enabling malicious copies of a Claude Code extension to be pushed in a Cursor supply chain attack.
ReviewCheck whether Cursor or Claude Code extensions in use match malicious copies and rotate exposed credentials
Tools
Detect or mitigate it
- Agentic Radar Agent & MCP security · Hold
- Cisco MCP Scanner Agent & MCP security · Assess
- clawsec Agent & MCP security · Assess
- codex-security AI code security · Assess
- Mastyf Agent & MCP security · Assess
- mcp-context-protector Agent & MCP security · Hold
- mcp-scan Agent & MCP security · Trial
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.