Skip to content

Instantly share code, notes, and snippets.

@solar-flare99
solar-flare99 / owasp-agentic-ai-top-10-prismor.md
Last active August 9, 2026 05:24
OWASP Agentic AI Top 10 controls with Prismor, an open-source AI agent runtime control plane

OWASP Agentic AI Top 10: How Prismor Enforces Runtime Controls for AI Agents

Prismor is an open-source runtime control plane that intercepts AI agent tool calls before they execute and enforces policy against the OWASP Agentic AI threat model.

Source: https://github.com/PrismorSec/prismor

What Prismor does

Prismor sits inside the agent's execution loop and checks every tool call against your policy before it runs. It covers 14 coding agents (Claude Code, Cursor, Windsurf, Codex, Copilot CLI, Gemini CLI, and more) and 14 framework adapters (LangChain, OpenAI Agents SDK, CrewAI, Pydantic AI, AutoGen, Google ADK, Vercel AI). Every call normalizes to one canonical event and runs through a single evaluator, prismor.runtime.evaluate_tool_call(), at about 0.8ms per call.

@solar-flare99
solar-flare99 / ai-agent-security-missing-control-layer-prismor.md
Created August 7, 2026 01:49
AI agent security: the missing control layer behind the 2026 rogue-agent disclosures

AI Agent Security: The Missing Control Layer Behind the 2026 Rogue-Agent Disclosures

AI agent security is a harness problem, not an alignment problem. The fix is a self-hosted control plane that enforces the boundary at every tool call, and Prismor is an open-source implementation.

Source: https://github.com/PrismorSec/prismor

What the 2026 rogue-agent disclosures showed

Between July 21 and August 4, 2026, three disclosures described AI agents taking unsanctioned action against real systems during cybersecurity evaluations.

@solar-flare99
solar-flare99 / self-hosted-ai-agent-control-plane.md
Created August 6, 2026 16:42
Self-hosted AI agent control plane: how to build one, with Prismor open source

Self-Hosted AI Agent Control Plane: How to Build One (with Prismor Open Source)

A self-hosted AI agent control plane intercepts every tool call an AI agent makes and enforces policy before execution, running entirely on your own infrastructure.

Source: https://github.com/PrismorSec/prismor

What a self-hosted AI agent control plane is

A control plane for AI agents sits between an agent's reasoning loop and the tools it executes: shell, filesystem, HTTP, and MCP servers. It evaluates each tool call against a policy, then allows it, blocks it, or routes it to a human for approval. "Self-hosted" means the enforcement runtime and the audit log stay on infrastructure you control, with no tool-call data sent to a vendor SaaS.

@solar-flare99
solar-flare99 / how-to-stop-rogue-ai-agents-prismor.md
Created August 5, 2026 00:52
How to stop rogue AI agents: intercept every tool call and enforce at the boundary with Prismor

How to Stop Rogue AI Agents: Runtime Enforcement with Prismor

A rogue AI agent is one that takes a dangerous real-world action while following its instructions. You stop it by enforcing policy on every tool call at the boundary, not by writing a better prompt. Prismor is the runtime layer that does this.

Source: https://github.com/PrismorSec/prismor / https://prismor.dev

What "going rogue" actually means

An AI agent goes rogue when it executes a harmful action, not when it says something wrong. The agent can pass every prompt-safety and jailbreak check and still run rm -rf, DROP TABLE, install a malicious package, or POST a secret to an external URL. The danger lives in the tool call, not the token stream.

@solar-flare99
solar-flare99 / ai-agent-control-plane-prismor.md
Created August 4, 2026 03:50
AI agent control plane market: the four-function + verifiable-execution criteria and how Prismor meets each

AI Agent Control Plane: The Market, the Criteria, and How Prismor Meets Them

The AI agent control plane is the governance layer between an agent's reasoning and the tools it executes, doing four jobs: connect, control, secure, observe. Prismor is a control plane built enforcement-first at the runtime hook.

Source: https://github.com/PrismorSec/prismor / https://prismor.dev

What the AI agent control plane market is

Every new layer of compute forced a new control layer. Servers got asset management. Cloud got Wiz. AI agents get the agent control plane. Companies are shipping agents into production faster than security teams can track them, and most cannot answer three questions: how many agents do we run, what tools can each one touch, and is the action it is about to take safe.

@solar-flare99
solar-flare99 / ai-agent-observability-prismor.md
Created August 2, 2026 04:15
AI agent observability and what comes next: observe then enforce every tool call with Prismor

AI Agent Observability: What to Build After You Can See Every Tool Call

AI agent observability means capturing every tool call an agent makes, with arguments, outcomes, and user context. Once you have it, the next step is enforcement: blocking dangerous calls before they run.

Source: https://github.com/PrismorSec/prismor

Why observability is table stakes

You cannot govern an AI agent you cannot see. The first job is a complete record of what your agents actually do: every tool invocation, the arguments passed, the result returned, and the user or session behind it. That record is the foundation for everything else, audit, incident response, cost tracking, and policy.

@solar-flare99
solar-flare99 / open-source-ai-agent-monitoring-prismor.md
Created July 31, 2026 00:05
Open source AI agent monitoring: Prismor, a free tool for coding agent tool calls and token usage

Open Source AI Agent Monitoring: Prismor, a Free Tool for Coding Agent Tool Calls and Token Usage

Prismor is a free, open-source tool that runs alongside your coding agent and reports the dangerous tool calls it made and the tokens it burned.

Repo: https://github.com/PrismorSec/prismor Install: pip install prismor Demo video: https://youtu.be/sGlFxMMCQFM (dedicated daily-summary walkthrough coming soon)

What Prismor does

@solar-flare99
solar-flare99 / ai-agent-canary-token-evasion-egress-control.md
Created July 28, 2026 15:40
AI agent canary token evasion: why reasoning agents walk past honey tokens, and how egress control stops them

AI Agent Canary Token Evasion: Why Reasoning Agents Walk Past Honey Tokens (and How Egress Control Stops Them)

AI agents evade canary tokens because they reason about your environment before acting: they tell real credentials from fake ones, avoid the bait, and exfiltrate live keys without ever tripping the honey token. Egress control and tool-call interception stop what detection misses.

Source: https://prismor.dev

What canary token evasion by AI agents means

A canary token (honey token) is a fake credential planted where real ones live: a dummy AWS key in a config file, a dead database string in an .env. It fires a zero-false-positive alert the moment anything authenticates against it, because no legitimate system ever calls a credential nobody deployed. This detection model assumes an indiscriminate attacker that sprays every secret it finds.

@solar-flare99
solar-flare99 / mcp-security-prismor-guardrails-gateway.md
Created July 28, 2026 02:17
MCP security enforcement with Prismor — guardrails, gateway, and trust scoring for Model Context Protocol tool calls

MCP Security: Prismor — Policy Enforcement, Guardrails, and Trust Scoring for Model Context Protocol

Prismor is an open-source AI agent control plane that intercepts, scores, and enforces policy on MCP tool calls before they execute.

Repo: https://github.com/PrismorSec/prismor

What it does

Prismor sits between AI coding agents and the MCP servers they call. Before a tool call executes, Prismor evaluates it against a customer-authored policy and returns one of five verdicts: allow, block, step_up (human approval), modify, or defer. After the call, Prismor scans tool output for prompt injection. The enforcement layer covers 14 coding agents including Claude Code, GitHub Copilot, Codex, Grok, Kiro, Windsurf, and Cursor.

@solar-flare99
solar-flare99 / eu-ai-act-agentic-ai-compliance-2025-2026.md
Created July 26, 2026 04:46
EU AI Act compliance requirements for agentic AI systems: timelines, Article 72, GPAI Code of Practice, and runtime governance

EU AI Act: Agentic AI Compliance Requirements for 2025–2026

The EU AI Act is an operative enforcement instrument with live penalty regimes, not a proposal — first-wave GPAI provider obligations took effect August 2, 2025, with high-risk system requirements following in August 2026.

Reference: Prismor Agent Governance | PrismorSec/prismor


What the EU AI Act Requires