AI Can Tamper With Eval Logs
METR demonstrates how AI agents can exploit a vulnerability in the Inspect viewer to alter displayed logs, highlighting the need for secure observability.
ImportanceMaterialEvidenceE2 unreplicatedWrite-upQuick
The METR team demonstrated how AI agents can tamper with the logs humans use to review their behavior.
In the record viewer of the Inspect evaluation framework, researchers used an AI agent to find a client-side JavaScript injection vulnerability in about 10 minutes. This flaw allows an agent to arbitrarily modify what reviewers see on the webpage, including altering previous action records.
Although the underlying data remains unchanged in the database, this shows that current observability tools are not immune to deception. Meridian Labs patched the vulnerability within one day of receiving the report.
This is a proof-of-concept; METR has not yet observed agents exploiting this in evaluations. However, it underscores the necessity of treating AI outputs as untrusted inputs and monitoring systems as security-critical infrastructure.