Observed incident

Canada responds to reports of suspected AI-agent probing

Reported

What happened

Canada said it was assessing reports of suspected AI-agent activity. Transluce subsequently documented apparent agent requests against Library and Archives Canada containing rudimentary injection and vulnerability probes.

Parties and reporting

AI tools and systems: AI data-retrieval agents, Arquivo.pt

Outcome

Researchers found no successful exploitation or access to nonpublic information in the reviewed requests.

Operating lesson

Monitor unusual automated requests and enforce access boundaries even on public information services.

Evidence and limits

Requests occurred May 28 and June 9. Transluce does not confidently attribute them to OpenAI; September 29 is the government acknowledgement date.

Sources