SLEUTH runs a complete digital-forensics investigation autonomously — raw disk, memory, and network evidence to a structured, fully-cited report, with no human in the loop. Run it as a standalone app, or plug it into AEGIS-AI as the SOC's tamper-evident evidence broker. The guardrail is an architecture, not an instruction.
⚠ INVESTIGATION STREAM SIMULATED · ALL FIGURES MEASURED — SEE docs/ACCURACY.md| Specialist | Failed | Correction | Result |
|---|---|---|---|
| memory | linux.pslist | derive OS profile → windows.info, re-run Windows plugins | caught + fixed |
| network | tshark (truncated PCAP −4096B) | editcap_recover → recovered.pcap → re-run tshark | 6/6 runs |
| memory | profile hint spoofed (corruption test) | validator re-executed linux.pslist, confirmed still fails | refuted = 0 trusted |
Disk, memory, and network specialists run in parallel over real SANS evidence (M57-Patents / LoneWolf 2018), then a validator re-executes every claim and an IR-narrator writes the report — every sentence carrying a [F-NNN] citation back to provenance.
Sleuth Kit + Plaso — filesystem timeline, MFT, tsk_recover. 34 confirmed findings on the primary case.
Volatility 3 — process injection, SSDT hooks, OS-profile derivation with hallucination recovery. 21 confirmed.
tshark + Zeek + Suricata (ET-Open) — beacon detection, truncated-PCAP recovery. 24 confirmed.
BLAKE3 content-addressed artifacts, Merkle-chained tool_calls hypertable, pgaudit on every SELECT. es cite F-NNN returns the whole trace.
Per-finding DB trigger + LISTEN/NOTIFY — no clock, no human input. Self-correction bounded to 3 retries per finding.
Memory-safe broker, Apache AGE attack graph, pgvector RAG grounding, pg_jsonschema argument validation.