DiggingBeagle / Audits
Technical reviews of exact artifacts, not guarantees that a project is safe.
DiggingBeagle selects public components and records what was inspected, the evidence behind each finding, and what remains untested. Machine observations are reviewed before publication; they are not automatically vulnerabilities or incident Cases.
1 published audits. 1 on this page.
Prompts & Instructions / review 1
Static review of the exact pinned six-line prompt. No machine observations or verified vulnerability were present; the referenced README and runtime environment were not supplied.
sha256:ce891d87c5ff937821a26e1e4bd66500014a78Snapshot reviewed; upstream currentness not checked
Read the dossierSearch all audit titles and summaries · Evidence methodology
Why this archive exists
DiggingBeagle is an independent research project documenting AI security incidents, agent failures, vulnerabilities and AI-assisted operations. A case keeps its claims beside the sources that support, contest or limit them. Later updates stay visible, so a reader can see when the account changed.
We publish case reconstructions, dated reporting and analysis across records. Each has a different evidentiary role. About the project and our methodology explain how the work is reviewed.