agentsastLast reviewed 2026-09-13
Index › Glossary › Continuous scanning and run-count coverage

Continuous scanning and run-count coverage

Direct answerRunning AI analysis repeatedly, on every commit and whenever models improve, on the premise that LLM bug finding is non-deterministic and coverage compounds with runs.

In more detail

zkao's continuous-security page cites an 8 percent per-run hit rate compounding to 96 percent over forty runs; its later Bron Labs post adds that under fixed models and prompts runs converge, so the harness matters more than repetition. Both statements are true and together they justify continuous scanning with evolving harnesses.

Tools that address it

zkao, Octane Security, Olympix.

False positive rate, Precision vs recall, Agentic scanning, LLM plus fuzzing, LLM plus symbolic execution or formal verification, Hallucinated vulnerabilities, Triage burden, Benchmark contamination, Human-in-the-loop, AI-assisted audit vs AI audit, Prompt injection in auditing pipelines, Responsible disclosure of AI-found bugs, Proof-of-concept harness, Threat model file, Severity calibration

Getting help

Firms on this index that handle this in practice: zkSecurity, Trail of Bits, Zellic, Nethermind Security.

Last reviewed 2026-09-13 by the agentsast editors. Machine-readable: data.json · summary.txt