AI Security Playbooks

Practical, field-tested guidance for securing agentic workflows, MCP toolchains, and AI-enabled browser automation.

DP-1 / Policy engine Detect Classify Evaluate Prompt Upload OAuth Tool call Allow In policy Review Policy issue Evidence retained for the policy decision
DP-1: Instructional header showing prompt, upload, OAuth grant, and tool call entering a policy engine. Production metadata: 3ls-dp-1-docs-policy-engine-diagram.svg; SVG master rendered fluidly with explicit 1600x1200 dimensions; placed as header companion on desktop and below hero copy on mobile.; task-1093-inline-svg-master
Visibility:
On-device collection brings supported AI activity into view for classification and policy evaluation.
Policy ownership:
Your organisation owns the policy evaluation and the resulting evidence.
DP-3 / Playbook Detect Classify Evaluate Step Boundary Evidence In policy Review Policy issue Evidence retained for the policy decision
DP-3: Compact playbook cover tile with handbook stack, control boundary motif, numbered badge, and evidence chip. Production metadata: 3ls-dp-3-playbook-cover-diagram.svg; SVG square master rendered in fixed card aspect ratio; crop-safe for playbook card thumbnails.; task-1093-inline-svg-master
Agentic Browser

Agentic Browser Security Playbook

Protect against prompt injection, cross-site actions, and data leakage in AI browser agents.

View Playbook
DP-3 / Playbook Detect Classify Evaluate Step Boundary Evidence In policy Review Policy issue Evidence retained for the policy decision
DP-3: Compact playbook cover tile with handbook stack, control boundary motif, numbered badge, and evidence chip. Production metadata: 3ls-dp-3-playbook-cover-diagram.svg; SVG square master rendered in fixed card aspect ratio; crop-safe for playbook card thumbnails.; task-1093-inline-svg-master
MCP

MCP Security Playbook

Control tool poisoning, prompt injection, and data exfiltration across MCP toolchains.

View Playbook
DP-3 / Playbook Detect Classify Evaluate Step Boundary Evidence In policy Review Policy issue Evidence retained for the policy decision
DP-3: Compact playbook cover tile with handbook stack, control boundary motif, numbered badge, and evidence chip. Production metadata: 3ls-dp-3-playbook-cover-diagram.svg; SVG square master rendered in fixed card aspect ratio; crop-safe for playbook card thumbnails.; task-1093-inline-svg-master
CI/CD

Agentic CI/CD Security Playbook

Prevent prompt injection and secret leakage in AI-driven build and deployment workflows.

View Playbook

From the blog

Companion Research

Playbooks explain what to do. These articles explain why those controls matter, using incidents, exploits, and runtime failure analysis.

Need Help Implementing These Controls?

3LS helps security teams deploy runtime guardrails for AI agents and tools.

Talk to 3LS Schedule Demo