T7 Rollback replay
The user revoked an access last week. The attacker copies the record from before the revocation over the newest record of the same user.
What stops it
Position plus a signed head: the sequence itself must be covered, not the records one by one.
What does not
Any store that verifies records independently, even with the owner bound in.
Today, measured 2026-10-07
- rejected on read
- Agent Memory reference runtime, SQLite canonical substrate, bucketed row digests, fail-closed open
- reported on audit
- inspeximus, receipts on, attacker holds the store directory, inspeximus, receipts on, attacker also holds the config home, langgraph-ledger over SqliteSaver, hash-chained ledger, verify_thread audit, memory-blackbox memory.md watcher, agent process alive, scan audit, memory-blackbox memory.md watcher, agent restarted before the scan, scan audit, Atelya Attest, keyed hash chain, verify_chain audit, Atelya Attest, keyed hash chain plus anchored head, verify and consistency audit, CONTINUUM event log, hash chain, verify_events audit, CONTINUUM event log, hash chain plus Ed25519-signed head, attest-verify audit
- accepted
- LangGraph SqliteSaver, LangGraph PostgresSaver, LangGraph RedisSaver, OpenAI Agents SDK SQLiteSession, LlamaIndex Memory, SQLAlchemy chat store, CrewAI long-term memory, LanceDB dataset, Vertex AI Agent Engine Memory Bank, managed store, edits through the data-plane API, Letta block checkpoint history, Mem0 local Qdrant store, inspeximus, receipts off (default), AtMem 2.3.7, audit chain alone, verify() audit, AtMem 2.3.7, audit chain with an external checkpoint outside the attacker-controlled store directory, verify() audit, acrf-memory-guard, per-entry HMAC over a JSON store
agmi-check --adapter agmi.adapters.langgraph_sqlite:LangGraphSqliteAdapter # runs T1 to T8; this is T7