Protocol pivoting: when MCP trust leaks into another agent protocol
Research on protocol pivoting shows how an injected instruction can cross from MCP into agent-to-agent delegation. Why per-protocol fixes miss it.
Blog
The SpanDock blog
News, how-tos and researched articles on AI coding tools, agents, MCP, cost and governance, from the SpanDock team.
Gemini 4 Argon is generally available: price, limits and the 1 December change
Gemini 4 Argon launched on 13 October 2026 at an introductory API price that doubles on 1 December. What it costs, what Google claims, and what to plan for.
6 min read
SWE-Bench Pro Verified: when coding agents were reading the answers
SWE-Bench Pro Verified closes gold-patch leakage channels and refines 102 tasks. Some model scores fall sharply once agents can no longer fetch the solution.
4 min read
Claude Code hooks can now fail closed when enforcement breaks
Claude Code v2.1.295 adds onFailure: block for command and HTTP hooks so missing scripts, timeouts and unexpected exits deny the action instead of failing open.
The ICO's agentic AI call for evidence: what engineering teams should prepare
The UK ICO's call for evidence on agentic AI runs 8 October to 20 November 2026. Map security, transparency and ADM evidence now.
4 min read
MCP Python SDK redirected custom headers off-origin
A medium-severity flaw in the MCP Python SDK followed cross-origin redirects and forwarded custom API keys. How it differs from the TypeScript OAuth issuer bug.
GPT-6.1 Sol: near-Astra coding performance at one-fifth the token price
OpenAI's GPT-6.1 Sol lists at $2/$10 per million tokens against Astra's $10/$50. What that changes for default coding models, caching and harness cost.
What the Bank of England told firms about autonomous AI risk
The September 2026 FPC Record treats frontier AI autonomy and open-weight models as cyber and ops resilience issues for firms.
5 min read
AI agents write more code; review still sets how much software ships
A 718-firm study finds AI agents raise code volume and PRs while resolved issues stay flat and review time rises sharply.
Copilot local sandboxing is generally available: what it actually restricts
Copilot local sandboxing is GA in the CLI, app and VS Code Agent Host. What OS limits cover, leave out, and how they sit with policy.
4 min read
MCP TypeScript SDK OAuth flaw: credentials followed the wrong issuer
A high-severity MCP TypeScript SDK flaw let the server choose which authorization server got client secrets. Patch, bind and rotate.
Claude Haiku 5.5 for coding sub-agents: what the price cut changes
Anthropic's Haiku 5.5 makes high-volume subagent work cheap enough to measure. When to route there, and when Sonnet still leads.
Browse by tag
- #Security (55)
- #Agents (41)
- #AI coding tools (38)
- #LLM costs (23)
- #MCP (16)
- #Evaluation (14)
- #Observability (12)
- #Compliance (11)
- #Enterprise (9)
- #Platform engineering (9)
- #Data privacy (8)
- #DevOps (7)
- #Model routing (7)
- #Open-weight models (7)
- #Research (7)
- #Tutorials (6)
- #Code review (4)
- #Developer productivity (4)
- #Guardrails (4)
- #Networking (4)
- #OpenTelemetry (4)
- #Budgets (3)
- #Prompt engineering (3)
- #Self-hosting (3)
- #MCP gateway (2)
- #Release notes (2)
- #Skills (1)
- #Testing (1)