Latest
●Prompt injection turns up in website HTTP headers, study finds●Nezha dashboard can be crashed by any low-privilege member●MCP Python SDK kept sessions forever, letting memory run out●Nginx UI flaws let MCP tools skip config security checks●Bank of America adds 1,000 contractors to fix Mythos-found bugs●UK stops short of AI rules in Cyber Security Bill●GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos●Attackers target critical Langflow flaw in 1,423 exploit attempts
Friday, 16 October 2026
1 agent hack today▼ 7 vs yesterday (8)
The Agentic TimesPowered byVortal

Incident database

Roo Code command approval bypass vulnerabilities (CVE-2026-110202 through CVE-2026-110206)

Multiple command approval bypass vulnerabilities discovered in Roo Code through version 3.54.0 allow attackers to execute denied shell commands through indirect prompt injection by exploiting parsing flaws in the auto-approval mechanism. These include bypasses via redirect operators, quote masking, command substitution, glob patterns, and command position attacks.

Disclosed 13 October 2026 · Record updated 13 October 2026

Impact

Multiple command approval bypass vulnerabilities allow attackers to execute arbitrary shell commands on developer machines without user approval through indirect prompt injection techniques.

Our coverage

Sources

  1. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-110202
  2. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-110203
  3. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-110204
  4. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-110205
  5. nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-110206