SpikeStrip
arcanum-sec/spikestripReversible HTML and JavaScript prompt decoys with opaque per-insertion keys.
adversarial-attackai-securitydefensive-tools+3
35
arcanum-sec/spikestripReversible HTML and JavaScript prompt decoys with opaque per-insertion keys.
ai45lab/privacytraceHow Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces
mordavid/bruteforceaiAdvanced LLM-powered brute-force tool combining AI intelligence with automated login attacks
maureille/agentic-pcapBenchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.
foxcornlab/thc-bloodmiamiAI chat-box pentesting tool in C: fires language (SQLi/NoSQL/XSS/SSTI) and prompt injection payloads at chat interfaces and flags the ones that bite
owasp/agentic-evidenceOWASP reference project for agentic AI security evidence: correlates agent execution, identity, tool calls, and authorization decisions into…
owasp/agentic-vulnerability-discovery-and-validation-harnessAgentic harness that automates vulnerability discovery and validation, orchestrating AI-driven analysis workflows to confirm exploitable findings.
asngs/agenttriage-open-sourceCross-agent tracing and security-diagnosis system for tool-using LLM agents: normalizes trace events, builds provenance graphs, extracts…
xhyumiracle/sudpSecret-Use Delegation Protocol — protocol-level secret use for agentic systems
owasp/xpsdReachability triage for vulnerability scans. Feeds scanner findings to an LLM agent that reads your source and decides which CVEs are actually…
peach-research-lab/authorizationbench[🎖️ Honorable Mention in HAIPS @COLM'26] The first benchmark to evaluate how well do LLM agents act in alignment with their assigned authorization…
owasp/piihunterScans PostgreSQL databases and Jira issues for PII using regex, NER/ML, and optional self-hosted LLM detection, with redacted reports and audit…
zentinelproxy/zentinelA security-first reverse proxy built to guard the free web.
zhengxr930/apex_officialDefender framework for LLM agent security that compiles task contracts, validates capability manifests, and checks effects via PLANT/WRAP proof…
nealbridges/vulnhunterAgentic AI security scanner that reasons like an attacker over source code, confirms exploitable flaws with executable PoCs, and drives test-first…
matijamiki/ranwhatFlight recorder and secret scanner for AI coding agents. Reads what Claude Code, Codex, Gemini CLI and 17 more ran, and flags risky actions and…
lzwhehe/benign-instruction-benchRe-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)
hackvertor/repeat-strikeBurp Suite extension that uses AI-generated regex strike rules to detect IDOR and access-control flaws, then scans proxy history to find similar…