ActiveSecHarness proposes capability tokens for coding agents
On 252 fixtures, the authors report Ring 0 blocked every attack fixture with zero false positives in 12.7 microseconds.
Stories per day · 30 days
Relatedprompt-injection2agentic-coding1capability-tokens1guardrails1living-off-the-land1llm-agents1open-weights1
2 stories, newest first · one card per story
Stories tagged #taint-tracking
External monitors outperform prompt guardrails against agent injection
On two Qwen2.5 models, a task-bound monitor admitted 1.3% and 7.7% of attacks after models proposed the attacker's call in 64% and 84%.