01
Latest briefPROMPT INJECTION
Prompt injection moved downstream
The weak point is often retrieval, orchestration, or hidden instructions.
SubscribeAI SECURITY BRIEF
AI Security Brief
Exploit paths, exposed surfaces, and ship risk for teams building AI.
Read it weekly. Act before the pattern spreads.
Prompt InjectionTool AbusePublic ExposureRelease Control
01Exploit Paths
how the break works
02Exposed Surfaces
what is reachable now
03Ship Risk
what should stop release
THIS WEEK
Signals worth reading
Short notes. Real attack paths. No security theater.
02
Operator noteTOOL ABUSE
Runtime permission is the blast radius
Fetch, shell, subprocess, and connectors decide how far a prompt can go.
Archive03
Proof layerPUBLIC EXPOSURE
Exposure turns theory into incident
OpenClaw shows which endpoints, docs, and agent interfaces are reachable now.
WatchboardTHREAT SURFACE
What AIPwn tracks
The surfaces where AI risk becomes reachable.
CURRENT TRACKING
01Input path
Prompt Injection
Instruction override, hidden tool calls, indirect poisoning, and retrieval chains.
02Runtime
Tool Abuse
Shell execution, downloader chains, connector misuse, and runtime permissions.
03Secrets
Secret Exposure
Leaked API keys, unsafe logs, public config artifacts, and long-lived credentials.
04Exposure
Public Surface
Open docs, unauthenticated endpoints, and exposed agent interfaces.
PROOF LAYER
Proof beats slides
OpenClaw turns findings into a live board: target, issue, status.
- Make exposure visible.
- Track docs, endpoints, auth, and runtime behavior.
- Reuse the same evidence in policy and gates.
OPENCLAW PREVIEWRecent exposed surfaces
TargetRiskIssueStatus
api.assistant-demo.aiHighPublic docs + no authPublic
tools.ops-agent.devHighShell-capable runtimeReview
rag-preview.exampleMediumPrompt injection pathTracked
share.agent-lab.runMediumLeaked token artifactRestricted
INFRASTRUCTURE
From brief to gates
The same evidence powers scanning, policy, and release control.
01
NEWSLETTER
AIPwn Newsletter
Weekly research on AI exploit paths, exposed surfaces, and ship risk.
Weekly02
CONTROL PLANE
ClawPlane
Policy, scanning, and release decisions for AI systems.
Alpha03
SCANNER
ClawScan
Evidence-first scanning across repos, prompts, connectors, and surfaces.
Research-fed04
GATE
ClawGate
Release gates for risky AI changes.
Alpha