Bright Security launches STAR Fuzzer for agentic application fuzzing
Original title: Bright Security Introduces STAR Fuzzer, Agentic Fuzzing That Writes Its Own Harnesses and Proves Every Finding
Bright says an open-source run found High or Critical issues in 45% of projects tested, with ten findings in eight projects.
Bright Security announced STAR Fuzzer, a mode of its Bright STAR platform that uses AI agents to pick security-critical functions and write harnesses, then an evolutionary engine to search for crashes, memory exhaustion and memory-safety bugs without a running application. The company says confirmed findings include a byte-exact payload and can be delivered in a pull request. It says the first open-source research run found High or Critical issues in 45% of projects tested, and the first month produced ten published findings in eight projects, including the Crystal standard library, htop and RIOT OS.
Unconfirmed: The 45% figure and the ten findings are Bright Security's own claims, not independently verified here.
- STAR Fuzzer is available now at brightsec.com/fuzzer.
- Named early targets include the Crystal standard library, htop and RIOT OS.
- The search engine is evolutionary, not an LLM, according to Bright.
- Bright says every finding is replayed in a fresh container before filing.
- Vendors
- Bright Security
- Products
- STAR FuzzerBright STAR
From the original article
10 min read at csoonline.com
Built on an evolutionary engine first released in 2018, STAR Fuzzer by Bright Security finds crashes, memory exhaustion and memory-safety bugs in security-critical code without a running application.
csoonline.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.