Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-08-29 · source-backed
CVE-2026-82021 (CVSS 9.0) covers Hermes Agent 0.18.2 through 0.19.0, where the bundled MCP catalog referenced a third-party upstream by branch name rather than commit SHA. Compromise the upstream and your code reaches every host installing that catalog entry, with zero operator action. The same batch includes CVE-2026-82020 (7.6), where ingested message content could overwrite the credential store because the sensitive-path guard excluded auth.json. Pinning is not optional in a catalog that executes what it fetches. (NVD)
Each link below shares sources, entities, or timing with this story.
CVE-2026-75130, published August 18, covers Upstash's Context7 through 2.1.2: the Custom AI Instructions feature serves unsanitized content through the MCP server, so poisoned instructions can exfiltrate credentials from environment files to an attacker-controlled service and...
The Model Context Protocol has a security problem that's no longer theoretical — it's statistical. Between January and February 2026, researchers filed 30+ CVEs against MCP servers, clients, and infrastructure. One package with nearly 500,000 downloads carried a CVSS 9.6 RCE....
Patched in EE 19.3.1, 19.2.5 and 19.1.7, covering everything from 18.9, CVSS 7.3. An authenticated user with only Developer permissions could get the agent to process configuration they control and execute arbitrary commands inside the CI context (NVD). The blast radius is wha...
Go look at your ~/.claude/CLAUDE.md right now. Mine has internal package names, a build command with a host in it, and notes about which credentials live where. I wrote it assuming exactly one reader. RuntimeWire published traced request captures on August 9 showing Muse Code...
Arctic Wolf published a critical advisory for a CVSS 10.0 vulnerability in the mcp-atlassian MCP server — one of the most widely deployed connectors linking agents to Jira, Confluence, and Bitbucket. A remote attacker with zero credentials can execute arbitrary code and pivot...
The agent skills supply chain is under coordinated attack. Snyk's ToxicSkills audit found 36% of ClawHub's 3,984 skills contain prompt injection payloads, 13.4% have critical malware, and submission rates exploded 10x to 500+/day. This week alone: CVE-2026-2256 (CVSS 9.1) is a...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.