The Wire.AI Security News and Incident Tracker

Lead dispatch

First reported horizon3.ai

Anthropic's super bug-hunting model Mythos is hardcore good at math, as latest vuln under attack shows

CVE-2026-61500, a critical authentication-bypass bug in Rejetto HTTP File Server (HFS) that enables full admin access and remote code execution, was discovered by Horizon3 researcher Zach Hanley using Anthropic's Mythos bug-hunting model and came under active exploitation within a day of disclosure. VulnCheck's canaries detected a China-hosted IP targeting vulnerable hosts in the US and Japan; a public exploit video was also published, and users should update to HFS v3.2.1 or later.
In the wild

ai-discovered-vulnerability · remote-code-execution · authentication-bypass
llm · ai-agents

Read the full dispatchQuery the index
Severity
0.72

The wire · latest

CLASS
AllThreatsNewsResearchAnalysisTools
TAGS
indirect-prompt-injectiontool-abusesupply-chaindata-exfiltration
More filters
TYPE
incidentresearchadvisoryanalysis
STATUS
In the wildPoCDisclosedPatched
Filteringmalicious-skills ×Clear all

First reported zenity.io

Attackers Target Agents via The Skill Supply Chain | Zenity Labs

Zenity Labs disrupted an active malware campaign that targeted AI agents through typosquatted 'skills' impersonating the Paperclip and Browser Use platforms, using trojanized Python/Node packages and a remote loader to deliver a second-stage credential harvester. The malicious skills accumulated over 1.7M aggregate installs on skills.sh, evaded scanners for weeks, and exfiltrated SSH keys, cloud credentials (AWS/GCP/Azure), and dozens of other secrets to attacker C2 at getpaperclipp[.]com; OWASP subsequently published a candidate Agentic Skills Top 10 with Malicious Skills at No. 1.
In the wildsupply-chainmalicious-skillsdata-exfiltrationtyposquattingtool-abuseai-agentsllmskillsmcpACTOR · Karli (karli-paperclip)
Details →

First reported arxiv.org

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills

SkillSieve is a hierarchical triage framework for detecting malicious AI agent skills—packages that combine natural-language SKILL.md instructions with executable code and inherit an agent's filesystem, credential, and network access. The framework layers recall-oriented regex/AST/metadata triage, four parallel LLM security sub-tasks, and a three-model debating jury, reaching F1=0.929 across 49,592 real ClawHub skills, a 390-skill benchmark, and 100 adversarial samples; code, labels, and results are open-sourced. Related audits (Snyk's ToxicSkills) reportedly found 13.4% of scanned skills contained critical issues including malware, prompt injection, and credential exfiltration.
researchprompt-injectionsupply-chaindata-exfiltrationtool-abusemalicious-skillsai-agentsllm
Details →
See the API docs to pull all 1344 items →

How the wire is made

Poll & cluster

Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.

Curate

AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.

Read the full methodology →

Every item here is one machine-curated intelligence object, not a headline.

Agentic AI ThreatsAI Security ResearchAgentic AI Security ToolsPrompt InjectionTool Abuse

Read the wire for free. There is a small charge to ask the index questions.

The wire, open

The complete curated feed, no key required.

Subscribe to the RSS feed

The vector desk

Query the index by meaning, not just keyword.

  • GET /api/items?tags=&minSeverity=&itemType=
  • GET /api/search?q= — keyword
  • GET /api/semantic?q= — vector
Preview semantic search