Anthropic launched OSS Scanner, a free opt-in service that runs periodic security scans of open-source projects using its strongest models. Project maintainers must sign up to participate. The reports are fully model-generated without human review, so some may be incorrect or invalid.
OSS Scanner launched, giving critical open source projects free, periodic vulnerability scans powered by the team's strongest models. Each finding ships with a proof-of-concept and, where possible, a patch.
OSS Scanner launched, giving critical open source projects free, periodic vulnerability scans powered by the team's strongest models. Each finding ships with a proof-of-concept and, where possible, a patch.
A scanning project reports AI model-rated security findings from open-source projects, with 77 critical and 803 high-severity issues already reported to maintainers. @thepunit shared a first-week update covering a curl fix and lessons learned, with more projects still being scanned.
A scanning project reports AI model-rated security findings from open-source projects, with 77 critical and 803 high-severity issues already reported to maintainers. @thepunit shared a first-week update covering a curl fix and lessons learned, with more projects still being scanned.
VibeGuard scans AI-generated codebases for common security flaws like unauthenticated API endpoints, hardcoded secrets, and SQL injection vulnerabilities. It uses LLMs to analyze code structure and flag risky patterns, helping founders who 'vibe code' with AI assistants avoid shipping insecure apps.
VibeGuard scans AI-generated codebases for common security flaws like unauthenticated API endpoints, hardcoded secrets, and SQL injection vulnerabilities. It uses LLMs to analyze code structure and flag risky patterns, helping founders who 'vibe code' with AI assistants avoid shipping insecure apps.
A Medium article by Samadhan Shimple outlines using agentic AI to run bug bounty hunting end to end, from reconnaissance through a submission-ready report, all from the command line. It presents the workflow as accessible with or without a paid AI subscription.
A Medium article by Samadhan Shimple outlines using agentic AI to run bug bounty hunting end to end, from reconnaissance through a submission-ready report, all from the command line. It presents the workflow as accessible with or without a paid AI subscription.