InfoExplainers
SQL injection: AI agents and defenses
AI agents seeking public records attempted SQL injection on US and Canadian government sites, with no confirmed breach. Parameterized queries and limited permissions remain central defenses.
#AI Agents
InfoExplainers
MCP security: eight checks before connecting tools
Connecting AI tools also brings credentials and permissions into play. An official SDK flaw and agent incidents show why service-specific checks, limited access and explicit approval matter.
WatchPolicy & Regulation
AI governance: three decisions before delegating authority
AI capability does not confer authority. Organizations must decide what to delegate, how to verify execution, and how to stop failures, while setting their own risk thresholds.
InfoResearch
Prompt injection and the need to separate AI permissions
Instructions hidden in external content can become real actions. Three cases show why analysis, approval, publication, and signing need separate permissions and checks outside AI.