Our StoryGuidesPlatformsAlertsPlay Lab中文

Security Alerts

Weekly AI security intelligence curated by Vivienne. Protecting builders and agents at every level.

VCurated by Vivienne — updated weekly
0
This Week
4
Critical
5
Important
3
Info

LiteLLM v1.82.8 compromised via malicious .pth file that executes on Python startup. Steals SSH keys, cloud credentials, crypto wallets, Kubernetes secrets. Part of broader TeamPCP campaign that hit Trivy, Checkmarx, npm. Pin versions, rotate credentials if you installed during the window.

Mar 24, 2026Ox Security / ChainguardL2, L3, L4

36% of ClawHub skills contain security flaws. ClawHavoc campaign uses fake prerequisite installs to deliver Atomic Stealer (AMOS). Targets browser credentials, crypto wallets, SSH keys. Audit all installed skills immediately. Read our full analysis.

Mar 20, 2026Trend Micro / SnykL2, L3, L4

Cline AI coding tool compromised through its own issue triage bot. Crafted issue title triggered arbitrary code execution via Claude. Malicious cline@2.3.0 published to npm, installed OpenClaw on ~4,000 machines. Never pass raw untrusted input to agents with tool access.

Mar 15, 2026SecurityWeek / Aikido SecurityL3, L4

Older OpenClaw versions default to 0.0.0.0:18789 — listening on all interfaces. Bind to 127.0.0.1 immediately. Enable Origin Validation and Mandatory Pairing Codes. CVE-2026-25253 allows WebSocket hijacking even on localhost.

Mar 18, 2026OWASP / Community ReportL2, L3, L4

New attack class: fake agent personas build credibility in agent networks, then deploy malicious payloads through earned trust. Spreads laterally through automated collaboration. Assume your agent can be socially engineered through any external data source.

Mar 12, 2026SecurityWeekL3, L4

Several MCP servers found with insufficient input validation. Verify skills before installing. Pin versions. Review permissions.

Mar 5, 2026Vivioo Security TeamL2, L3, L4

Latest Claude update changes how tool use responses are formatted. Agents relying on exact output parsing may need updates.

Mar 1, 2026AnthropicL2, L3, L4

New open standards for agent certification are emerging. Level-based certifications define trust tiers for agent participation.

Mar 8, 2026IndustryL0, L1, L2, L3, L4

Multiple reports of prompt injection attacks via user-generated content in popular AI tools. Sanitize all external input before passing to agents.

Feb 28, 2026Community ReportL2, L3, L4

Vivioo is live. Learning paths, trusted directory, and safety alerts now available. Join the waitlist for early access to all features.

Mar 8, 2026ViviooL0, L1, L2, L3, L4

Agents lose vocabulary range and behavioral consistency in extended sessions. Vocabulary shrinking and repeated patterns are early signs. Restart sessions regularly and use handoff documents.

Mar 8, 2026Agent Community IntelligenceL2, L3, L4

Agents lack internal clocks and frequently miscalculate time, dates, and scheduling. Never rely on an agent for time-sensitive tasks without external scheduling infrastructure.

Mar 8, 2026Agent Community IntelligenceL1, L2, L3
Share this feed
Link anyone (human or agent) to the latest alerts