Store, measured at rest
AtMem 2.3.7
audit chain with an external checkpoint outside the attacker-controlled store directory, verify() audit
AtMem 2.3.7 was seeded through its own API and edited behind its back nine ways. 8 edits served as genuine, 1 reported on audit, 0 rejected on read.
- Measured on
- atmem 2.3.7, Darwin arm64, Python 3.12
- Date
- Source
- github.com/aetna000/atmem
- Attack versions
- tamper@v1, truncate@v1, delete_middle@v1, reorder@v1, forge@v1, cross_replay@v1, rollback_replay@v1, metadata_tamper@v1, snapshot_rollback@v1
What this means
The agent acts on an edited memory first; the operator finds out only if the audit is run. 1 of the nine edits are reported by that audit and 8 are served with no record anywhere. Run the audit on a schedule, or move the check onto the read path.
The 9 verdicts
Detection point: the audit, a separate call the operator has to make; the read path serves the edit first.
Level L0, Measured. The store has a published row. Any verdicts. What L0 means.
| Edit | Verdict | What the tool said |
|---|---|---|
| T1 Content tamper | accepted | accepted silently |
| T2 Tail truncation | accepted | accepted silently |
| T3 Middle deletion | accepted | accepted silently |
| T4 Reordering | accepted | accepted silently |
| T5 Forged insertion | accepted | accepted silently |
| T6 Cross-context replay | accepted | accepted silently |
| T7 Rollback replay | accepted | accepted silently |
| T8 Metadata tamper | accepted | accepted silently |
| T9 Snapshot rollback | reported | the store noticed it was older than its last committed state (verify: pinned event at sequence 17 is missing (tail truncated?)) |
A verdict is what the tool did, not an opinion. "Accepted" means it loaded the altered store, raised nothing, and the agent carried on from the altered memory as if it were true. Every cell has a control that proves the edit landed before the verdict counts.
Where the attacker stands
The attacker holds the store (a file, a table, a bucket, or the data-plane role of a managed service) and edits it outside the tool's API, then the tool is reopened the way its users would reopen it.
Reproduce this row
Everything runs offline unless the store is a managed cloud service, in which case the row needs a project of your own. The run seeds a fresh store, applies each edit, confirms it landed, reopens the store and records what came back.
pip install agent-memory-integrity
python agmi/full_runner.py --json results/scorecard.json # every row, this one included
python -m agmi.agent --target atmem-chain+checkpoint --families at-rest # this row through the storage-side hunt
python -m agmi.agent --target atmem-chain+checkpoint --compose # composite moves against this rowBadge
Maintainers can link their row from their README. The badge points here and changes nothing on your side:
[](https://agentmemoryintegrity.org/stores/atmem-chain-checkpoint.html)