// artifact family
adversarial ai / agentic forensics — deep
70 browser-only forensics tools in this catalog group — browse by artifact family when you know the kind of evidence you are working with, not the investigation pattern.
tools in this family
ordered as in the forensics catalog. every tool runs locally — no upload, no account.
- ai agent autonomous action accountability tracerdrop agent run log · trace responsibility for each autonomous action · runs locally
- ai agent multi step transaction graph builderdrop agent run log · build graph of agent actions across steps · runs locally
- ai agent network exfiltration pattern detectordrop agent network log · detect data exfiltration via agent · runs locally
- ai agent persistence mechanism detectordrop agent + system state · detect persistence implanted by agent · runs locally
- ai agent tool call execution trace reconstructordrop agent run log · reconstruct tool-call sequence + state mutations · runs locally
- mcp client invocation log forensic analyzerdrop mcp client invocation log · parse server calls + arguments + responses · runs locally
- mcp model context protocol server audit log forensic analyzerdrop mcp server audit log · parse tool calls + resource accesses + auth · runs locally
- mcp prompt injection via tool result detectordrop mcp server tool result log · detect injection payloads in tool responses · runs locally
- mcp server permission escalation detectordrop mcp server audit log · detect over-permissioned tool exposure · runs locally
- mcp tool call graph reconstructordrop mcp client + server log set · reconstruct tool-call dependency graph · runs locally
- ai agent credential handling auditdrop agent run log · audit credential usage + leakage risk · runs locally
- ai agent file system modification trace builderdrop agent run log + filesystem snapshot · reconstruct fs changes attributable to agent · runs locally
- ai agent prompt vs action divergence detectordrop agent run log · detect actions taken inconsistent with prompt · runs locally
- anthropic mcp claude tool call attribution tooldrop claude tool call log · attribute each tool call to model decision · runs locally
- autogen orchestration log forensic analyzerdrop autogen orchestration log · parse agent collaboration · runs locally
- crewai orchestration log forensic analyzerdrop crewai orchestration log · parse agent collaboration · runs locally
- langgraph orchestration log forensic analyzerdrop langgraph orchestration log · parse node transitions + state · runs locally
- ollama local inference log forensic analyzerdrop ollama log · parse local inference activity + model usage · runs locally
- openai function call attribution tooldrop openai function-call log · attribute each call · runs locally
- vllm inference server log forensic analyzerdrop vllm server log · parse inference requests + cache hits · runs locally
- llamacpp local inference log analyzerdrop llama.cpp log · runs locally
- lm studio local inference log analyzerdrop lm studio log · runs locally
- lora fingerprint identifier image modelsdrop image samples · detect lora fingerprint signatures (sd / flux) · runs locally
- lora fingerprint identifier text modelsdrop text samples · detect lora fingerprint signatures · runs locally
- model card vs actual weights mismatch detectordrop model card + weights · detect claims that don't match actual model · runs locally
- model checkpoint tampering detector ggufdrop two gguf models · diff quantized weights + metadata · runs locally
- model checkpoint tampering detector onnxdrop two onnx models · diff graphs + weights · runs locally
- model checkpoint tampering detector pytorchdrop two pytorch checkpoints (.pt / .pth / .bin) · diff weights + detect targeted poisoning · runs locally
- model checkpoint tampering detector safetensorsdrop two safetensors checkpoints · diff weights · runs locally
- tgi text generation inference log analyzerdrop tgi server log · runs locally
- embedding model fingerprint identifierdrop embedding vectors · identify which embedding model produced them · runs locally
- fine tune backdoor trigger detectordrop fine-tuned model + test prompt set · detect backdoor triggers · runs locally
- fine tune dataset pii residue detectordrop fine-tune jsonl · detect pii residue · runs locally
- fine tune dataset poisoning pattern detectordrop fine-tune dataset · detect poisoning patterns · runs locally
- lora adapter weight fingerprint extractordrop lora adapter file · extract identifying weight fingerprint · runs locally
- synthetic data poisoning in training set detectordrop training set · detect synthetic poisoning · runs locally
- vector store embedding extraction attack detectordrop similarity search log · detect embedding-extraction patterns · runs locally
- vector store leakage via similarity search detectordrop similarity search query log · detect data exfiltration via similarity queries · runs locally
- vector store membership inference attack detectordrop vector store query log · detect membership inference probing · runs locally
- vector store poisoning pattern detectordrop vector store + provenance log · detect poisoning insertions · runs locally
- rag document leak detectordrop llm output corpus + source documents · detect verbatim or semantic leakage · runs locally
- rag retrieval anomaly detectordrop rag retrieval log · detect anomalous retrieval patterns · runs locally
- rag prompt injection via retrieved doc detectordrop retrieved docs · detect injection payloads in retrievals · runs locally
- rag attribution vs actual source mismatch detectordrop rag output with attributions · detect attribution mismatch with retrieved chunks · runs locally
- prompt injection campaign attribution tooldrop set of injection attempts · cluster + attribute to authors · runs locally
- jailbreak prompt corpus pattern matcherdrop observed prompt · match against known jailbreak families · runs locally
- jailbreak corpus evolution trackerdrop time-series of jailbreaks · track evolution + variant emergence · runs locally
- llm context window leak detectordrop llm output · detect leakage of system prompt or other contexts · runs locally
- llm tokenizer fingerprint identifierdrop text sample · identify tokenizer signature · runs locally
- synthetic media tool attribution imagedrop generated image · attribute to midjourney / sd / dall-e / flux / ideogram · runs locally
- synthetic media tool attribution videodrop generated video · attribute to runway / sora / veo / kling · runs locally
- synthetic media tool attribution audiodrop generated audio · attribute to elevenlabs / playht / suno / udio · runs locally
- ai watermark presence detector textdrop text · detect known text watermarking signatures (kirchenbauer / synthid etc) · runs locally
- ai watermark presence detector imagedrop image · detect known image watermarks (synthid / stable signature) · runs locally
- ai watermark presence detector audiodrop audio · detect known audio watermarks (audioseal / synthid-audio) · runs locally
- prompt engineering attribution style fingerprinterdrop set of prompts · cluster by author style · runs locally
- anthropic constitutional ai rejection log analyzerdrop claude api rejection log · parse rejection reasons · runs locally
- openai moderation api rejection log analyzerdrop openai moderation rejection log · parse rejection reasons · runs locally
- huggingface model card tampering detectordrop two model card versions · diff claims · runs locally
- inference cost spike anomaly detectordrop inference cost log · detect anomalous spikes · runs locally
- ai judge scorer manipulation detectordrop ai-judged eval log · detect manipulation patterns · runs locally
- adversarial example detector input screenerdrop input image · detect adversarial example patterns · runs locally
- ai coding assistant commit attribution tooldrop git commit set + ide telemetry · attribute commits to ai vs human · runs locally
- ai pair programming session deep reconstructordrop cursor / copilot / windsurf / continue session log · reconstruct ai-assisted edits per file · runs locally
- ai generated code license compliance tracerdrop ai-generated code + known training corpus signatures · detect potential license issues · runs locally
- anthropic api usage log forensic analyzerdrop anthropic api usage log · parse model + token + cost per key · runs locally
- openai api usage log forensic analyzerdrop openai api usage log · parse model + token usage per key · runs locally
- api key leakage into prompt detectordrop prompt corpus · detect api keys / secrets leaked into prompts · runs locally
- multi agent collusion pattern detectordrop multi-agent run log · detect collusion or echo-chamber patterns · runs locally
- agentic on chain action forensic tracerdrop ai agent log + on-chain tx history · trace ai-driven on-chain actions · runs locally