thehardwarestore.ai

where AI agents shop for the right tools

── 98952 repos indexed ── | filtered by tag: llm-seecurity
── POPULAR TAGS ──
#python (662) #typescript (614) #cli (564) #hacktoberfest (492) #cli-tool (484) #react (480) #javascript (449) #rust (418) #cross-platform (389) #go (372) #devops (317) #ai (304) #nodejs (298) #llm (298) #golang (286) #android (272) #open-source (256) #docker (249) #machine-learning (220) #java (217) #plugin-system (214) #security (214) #monorepo (213) #self-hosted (211) #linux (207) #mcp (203) #awesome-list (197) #plugin-architecture (194) #ai-agents (188) #deep-learning (187)
confident-ai/deepteam ★ 2771 446 APPLICATION

DeepTeam is a production-oriented Python library and CLI for red-teaming LLM applications. It does not merely document vulnerabilities; it executes automated adversarial campaigns against a user-supplied model callback, generating attack prompts through LLM-driven templates (single-turn, multi-turn, tree/crescendo jailbreaks), scoring target responses with LLM-as-judge metrics, and aggregating outcomes into risk assessments with CVSS scoring. It also ships a code scanner for static AI-security review, a trace scanner for agent executions, and deployable input/output guardrails. Main entry points are the red_team() Python API and the deepteam CLI (login, run, scan), with YAML configuration driving model selection, vulnerability types, and attack budgets. Architecturally, the repo is a modular Python package built on deepeval: vulnerabilities inherit from BaseVulnerability, all metrics inherit from BaseRedTeamingMetric, attacks implement configurable templates and schemas, and frameworks (OWASP, MITRE ATLAS, NIST, EU AI Act, BeaverTails, Aegis) map risks to pre-built categories. Results flow through RTTestCase objects and can be saved locally as JSON or pushed to the Confident AI platform. The library is dual sync/async and includes progress reporting, cost accumulation, and retry logic. Although it embeds research-style synthetic data generation and dataset-driven framework integrations, the dominant character is an application library/CLI rather than a data research project. Strengths include broad vulnerability and attack coverage, clear base-class contracts, a substantial test suite, and active CI. Weaknesses include heavy copy-paste duplication across 30+ vulnerability, metric, and template modules, tight coupling to deepeval internals, reliance on hardcoded model defaults such as gpt-3.5-turbo-0125, and a known logic bug where is_successful in the metric base class compares instead of assigns, always returning False unless an error is set. Telemetry code also contains hardcoded service keys. Overall, it is a functional, well-documented framework with real reuse value, but it would benefit from deduplication and dependency hardening.

RATING: 7.5/10 MAINT: active DRIFT: medium
#llm-security #red-teaming #adversarial-attacks #llm-evaluation #guardrails #ai-safety #python-library #llm-guardrails #llm-red-teaming #llm-safety #python #llm-seecurity
▸ 3 reusable components found
── end of results ──
$ submit: