What MITRE ATLAS Publish Poisoned AI Agent Tool (AML.T0104) - Resource Development adversarial technique against AI systems requires
This node addresses MITRE ATLAS technique AML.T0104 (Publish Poisoned AI Agent Tool), an adversarial technique in the ATLAS Resource Development tactic. Adversaries may create and publish poisoned AI agent tools. Poisoned tools may contain an llm prompt injection, which can lead to a variety of impacts. Tools may be published to open source version control repositories (e.g. GitHub, GitLab), to package registries (e.g. npm), or to repositories specifically designed for sharing tools (e.g. OpenClaw Hub). These registries may be largely unregulated and may contain many poisoned tools [\[1\]][1]. Tools may also be published as remotely hosted servers [\[2\]][2]. [1]: https://opensourcemalware.com/blog/clawdbot-skills-ganked-your-crypto [2]: https://mcpservers.org/remote-mcp-servers Defending against this technique is required under EU AI Act (accuracy, robustness and cybersecurity), NIST AI RMF, and ISO/IEC 42001 obligations; this node operationalises the documented ATLAS mitigations and cross-instrument controls into a deterministic verification workflow.
Pillar: AI Governance & Law · Authority: MITRE Corporation · Version: 1.0.1 · Last updated:
Primary source: https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0104
SHA-256 integrity: ede595b539236917e3dff6f67cd6cfd1ab7b490d9b81777f2cc6612219c3fdee
Primary Citations — 7 traced to source
- MITRE ATLAS - Publish Poisoned AI Agent Tool (AML.T0104), https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml#AML.T0104, AML.T0104 technique entry, 2026
- EU AI Act - Regulation (EU) 2024/1689 on Artificial Intelligence, https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689, Article 15 (Accuracy, Robustness, Cybersecurity), 2024
+ 5 more citations (full bibliography, deterministic workflow, actionable schema and crosswalks) included in the vault unlock — $0.01 via Skyfire / L402 / Direct Base USDC.
Access
- Discovery (free): /api/v1/nodes/mitre-atlas-publish-poisoned-ai-agent-tool.json — 6-field metadata
- Vault (full node): /api/v1/vault/nodes/mitre-atlas-publish-poisoned-ai-agent-tool.json — full 13-key payload, $0.01 USDC (L402/Skyfire/Direct Base)
- Canonical URL: https://bidda.com/intelligence/mitre-atlas-publish-poisoned-ai-agent-tool
- Back to registry: Browse all 10,108 compliance nodes