Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 7 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

Multiple OpenClaw AI assistant vulnerabilities disclosed, including prompt injection paths

Five CVEs were published for the OpenClaw personal AI assistant (formerly Clawdbot) covering prompt injection via untrusted Slack channel metadata and unsanitized workspace paths, a misleading macOS deep-link confirmation dialog that could lead to arbitrary command execution, local file exfiltration via the Feishu extension's sendMediaFeishu tool, and path traversal in browser download helpers. All issues were fixed in releases 2026.2.3 through 2026.2.15.

Disclosed 19 February 2026 · Record updated 13 September 2026

Impact

Attackers able to influence Slack channel metadata, workspace directory names, tool calls or deep links could inject instructions into the agent's system prompt, exfiltrate local files such as /etc/passwd, write files outside the intended downloads directory, or trick users into approving commands that differ from the visible preview, potentially leading to arbitrary command execution.

Our coverage

No articles linked to this incident yet.

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-24764
  2. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-26320
  3. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-26321
  4. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-26972
  5. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-27001