AI Threat Alert
AI Component
Agent
AI agent frameworks (AutoGPT, CrewAI, LangGraph, etc.) orchestrate LLM-powered autonomous actions. Their tool-use capabilities create unique attack surfaces not present in simple chat interfaces.
301
Total CVEs
16
Pages
Page 15 of 16
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| MEDIUM | GHSA-vr5g-mmx7-h897 | OpenClaw: SSRF bypass via interaction-triggered navigation | openclaw | - |
| MEDIUM | GHSA-67mf-f936-ppxf | OpenClaw: scope misconfiguration enables unauthorized node pairing | openclaw | - |
| LOW | GHSA-5fc7-f62m-8983 | OpenClaw: local file read bypasses workspace policy | openclaw | - |
| MEDIUM | GHSA-3fv3-6p2v-gxwj | openclaw: SSRF bypass in QQ Bot media fetch paths | openclaw | - |
| MEDIUM | GHSA-5h3f-885m-v22w | openclaw: WS sessions persist after gateway token rotation | openclaw | - |
| LOW | GHSA-25wv-8phj-8p7r | OpenClaw: auth rate-limit bypass via async race condition | openclaw | - |
| HIGH | GHSA-5wj5-87vq-39xm | openclaw: auth bypass enables exec escalation on reconnect | openclaw | - |
| MEDIUM | GHSA-vc32-h5mq-453v | OpenClaw: cross-channel allowlist write bypass | openclaw | - |
| MEDIUM | GHSA-68x5-xx89-w9mm | OpenClaw: stale auth closure bypasses gateway access control | openclaw | - |
| MEDIUM | GHSA-cmfr-9m2r-xwhq | OpenClaw: auth bypass enables persistent browser profile mutation | openclaw | - |
| MEDIUM | GHSA-whf9-3hcx-gq54 | OpenClaw: token rotation bypasses role approval | openclaw | - |
| MEDIUM | GHSA-qqq7-4hxc-x63c | openclaw: local file exfiltration via trusted MEDIA refs | openclaw | - |
| MEDIUM | GHSA-q2gc-xjqw-qp89 | OpenClaw: eval approval bypass enables unintended code exec | openclaw | - |
| LOW | GHSA-cm8v-2vh9-cxf3 | openclaw: git env var injection enables host redirect | openclaw | - |
| HIGH | CVE-2026-40113 | PraisonAI: arg injection injects env vars into Cloud Run | praisonai | 8.4 |
| HIGH | CVE-2026-40116 | PraisonAI: unauth WebSocket drains OpenAI API credits | praisonai | 7.5 |
| UNKNOWN | CVE-2026-40111 | PraisonAI: RCE via shell injection in memory hooks executor | praisonaiagents | - |
| MEDIUM | CVE-2026-40112 | PraisonAI: XSS via no-op HTML sanitizer in agent output | praisonai | 5.4 |
| MEDIUM | CVE-2026-40117 | PraisonAI: arbitrary file read via unguarded skill tool | praisonaiagents | 6.2 |
| HIGH | CVE-2026-40150 | PraisonAIAgents: SSRF exposes cloud metadata via web_crawl | praisonaiagents | 7.7 |