Falcon uses execution traces to verify secure agentic code
The framework ties security rewards to real program behavior during test-time repair and reinforcement learning.
Stories per day · 30 days
2 RSS
Relatedcoding-agents2claude1cursor1execution-traces1idor1project-codeguard1reinforcement-learning1verification1
6 stories, newest first · one card per story
Stories tagged #secure-coding
Datadog tests security rules on coding agents' secure code
Without rules, Sonnet 5, Composer 2.5, and GPT 5.5 all left IDOR flaws in a document portal.
1
Newer and Bigger, but Safer? A Longitudinal Study of the Functionality-Security Gap in LLM-Generated Code
Across 32 LLMs, newer models are safer in absolute terms, but no family closes the code security gap.
Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks
A 267-word specification frame cut security defects in code from five frontier models, and never made any model worse.
Compiler Can Undo Your Security Checks
Chris Domas explains at Black Hat how legal compiler optimizations can strip security checks and memory-clearing operations, turning secure C source into vulnerable binaries.
Putting models to the secure coding test: Plan vs default mode
Datadog Security Labs tested Sonnet 5, Composer 2.5, and GPT 5.5 to see if plan mode yields more secure code than default mode.