5 posts tagged with “supply-chain”
A fake-font credential stealer landed in 12,137 GitHub repos between October 14 and 16, about 130 times the cluster in the only write-up so far. It goes straight for Claude Code, Gemini and OpenAI credentials. We found malware in nine forks of REA.
A tidy-up PR removed a safety pattern from a Snowflake workflow. Five days later an autonomous agent had a Jira token. The headlines said an AI wrote the bug; the commit history cannot actually tell you who did, and that is the more serious problem.
Five CVEs across four vendors in thirteen months, all the same bug: your coding agent trusts a directory, then executes a file that can change underneath it. Here is the pattern, and the one line in Claude Code's restricted mode that actually fixes it.
820 malicious packages. 30,000 exposed instances. Fortune 500 breaches. The AI agent ecosystem has a supply chain problem that traditional AppSec isn't built to catch.
Nineteen malicious npm packages. Four AI coding tools. Rogue MCP servers injected silently into agent configurations. SANDWORM_MODE is the first documented autonomous supply chain attack targeting AI developer toolchains — and it exposes a structural vulnerability that identity alone cannot fix.