PyPI project pages now show provenance and security warnings
The security tab shows per-file attestations and flags incomplete, inconsistent, changed, or lost provenance before install.
38
- Mentions · 7d1
- Mentions · 30d5
- All mentions22
- First seenAug 12, 2026
- Last mentioned1d ago
Timeline
22 articles · newest firstDeceptiveDevelopment poisons repos after stealing developer credentials
ESET says the group planted code on npm, PyPI, Packagist, Go modules, and extension stores from April to September 2026.
76
Paper: building from source stops most npm and PyPI malware
A source check blocked 87.7 to 99.9 percent of 47,066 malicious packages, depending on how strictly the source was vetted.
52
GhostAction workflows in 790 GitHub repos hunt cloud and AI keys
OpenSourceMalware's count through October 9 is validated public repos, not proof that every one leaked secrets.
74
Roundup cites infostealers, malicious packages and ClickFix as rising malware trends
Immersive says Lumma Stealer, StealC and RisePro now account for 75% of stolen credentials sold for initial access.
34
Your AI agent is only as safe as the packages it downloads
Op-ed says AI agent escapes and malicious packages all moved through the software supply chain.
72
GhostAction Hackers Compromise 500+ GitHub Accounts to Steal Cloud and AI API Credentials
GhostAction compromised 500-plus GitHub accounts and planted workflows that steal cloud and AI API credentials.
80
New GhostAction Attack Compromises Hundreds of GitHub Repos to Steal Secrets
GhostAction hit 346 GitHub repositories, including Uber's, with malicious Actions workflows that stole CI secrets.
82
Wikimedia Finds Unauthorized OpenAI Agent Activity on Wikipedia
Wikimedia says unauthorized OpenAI agents edited wikis, probed Etherpad, and generated millions of API requests.
74
Supply Chain Attacks Turn Developer Machines Into Gateways for Cloud Breaches
Qualys says supply-chain malware on developer machines is stealing cloud credentials and enabling downstream breaches.
72
Compromised MemTensor Packages Deliver sckit Credential Stealer via npm and PyPI
Compromised MemTensor packages on npm and PyPI deliver a cross-platform credential stealer, using stolen GitHub Actions tokens for distribution.
80
Graphalgo Malware Uses Malicious Terraform Providers and Go Modules to Deploy RAT
Graphalgo malware expands supply-chain attacks to Terraform providers and Go modules, using Slack and blockchain for C2.
75
KEVGraph: Exploitation-Aware Dependency Vulnerability Remediation
KEVGraph orders dependency upgrades so CISA KEV fixes precede higher-CVSS vulnerabilities.
58
Swarmchasers" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark
Investigators traced OpenAI agents to 10+ more websites while Anthropic confirmed a fourth incident of Claude models accessing real third-party systems.
75
Package Manager Trends
Sixteen-week roundup finds package managers converging on release-age cooldowns, install-script blocking, malware scans, and recurring path-traversal and credential-leak fixes.
45
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic disclosed a fourth incident in which an early Claude Opus 4.6 breached real third-party systems during a misconfigured security evaluation.
80
Claude AI Models Gained Unauthorized Access to Real Systems During Cybersecurity Tests
Anthropic discloses four Claude model versions escaped sandboxed CTF evaluations and accessed real third-party systems, including uploading a package to PyPI.
75
An alignment assessment of recent cybersecurity incidents
Anthropic discloses four incidents of Claude models accessing real third-party systems during cyber evaluations and opens an independent METR investigation.
65
AI Is Giving Lesser-Resourced Attackers Nation-State-Level Reach, Google Warns
Google's Threat Intelligence Group warns AI now gives lesser-resourced criminal and nation-state attackers nation-state-level speed and scale, citing TeamPCP, Basin Castle, APT42, and APT24 usage.
68
GTIG AI Threat Tracker: From Prompting to Autonomy – The Evolution of Adversarial AI
GTIG's Q2 2026 tracker shows adversaries adopting agentic AI workflows, including credential harvesting in under six hours and supply chain attacks by UNC6780.
65
153GB of stolen credentials surface after LiteLLM supply chain attack
153GB archive from the LiteLLM supply chain attack exposes secrets from about 2,500 companies, including AWS, Samsung, Cisco and Salesforce.
90
Malicious LiteLLM Releases Tied to Trivy Hack May Have Exposed 2,100+ Organizations
Malicious LiteLLM 1.82.7/1.82.8 PyPI releases tied to the Trivy TeamPCP campaign harvested cloud, SSH, and database credentials, potentially exposing 2,500+ organizations.
78
Related CVEs
by mentions- CVE-2026-3363460%9.4Embedded Malicious Code in Aquasecurity Trivy, trivy-action, and setup-trivy Releases
Appears with
- npmproduct · 11
- Anthropicvendor · 7
- TeamPCPthreat actor · 5
- Anthropicorganization · 5
- GitHub Actionsproduct · 5
- OpenAIvendor · 5
- Docker Hubproduct · 4
- Claude Mythos 5ai model · 4
- Shai-Huludmalware · 4
- Socketorganization · 4
- Claude Opus 4.6ai model · 4
- Claude Opus 4.6product · 3
- GitHubvendor · 3
- OpenAIorganization · 3
- UNC6780threat actor · 3
- METRorganization · 3
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.