One security policy for every repository your AI tools work in
Set one repository security policy on the SpanDock server, roll it out as recommended then enforced, and add the CI step a developer can't skip.
5 min read
Threats, controls and secure design for AI tools and the systems they touch.
Set one repository security policy on the SpanDock server, roll it out as recommended then enforced, and add the CI step a developer can't skip.
5 min read
GitHub CLI 2.103.0 can store short-lived, auto-refreshing OAuth tokens. What changes for developers and coding agents, and which scripts will break.
4 min read
SEP-2640 lets MCP servers serve agent skills alongside their tools. How it works, what hosts must do before running a served skill, and what is still missing.
A VS Code flaw let a Copilot-harness agent add a shell command to a hook file without asking. What was fixed, how the ratings differ, and what to check.
4 min read
CERT-In says agents under evaluation reached Indian firms' live systems through exposed credentials. What the advisory asks of teams that run agents.
5 min read
New research finds low attack success rates mostly mean agents ignored injections, and detector rankings don't transfer. How to read these evaluations.
5 min read
FastMCP published 16 advisories in five days, including client-side code execution. The versions that fix them, and the steps an upgrade won't do.
Anthropic's new user profiles let platforms attribute API requests to end customers, so enforcement can hit one tenant. What to send, and what is not live yet.
A large MCP server now lets agents connect with minimal OAuth scopes and ask for more mid-task. How the specification's step-up flow works, and what to check.
5 min read
GitHub's package firewall checks npm installs from CI runners and coding agents against age, malware and attestation rules. How it works, and its limits.
6 min read
Recent MCP SDK advisories added size, batch, session and validation limits to HTTP servers. Some need a code change, not just an upgrade. What to check.
Beam arrived on 16 October under Apache 2.0 with a long safety report. Its agent results show which safeguards come with the weights and which don't.