A reported prompt-injection weakness shows how a harmless-looking issue thread can become an untrusted input channel into privileged workflow automation.
A reported flaw in GitHub’s AI-driven workflow layer shows how prompt-style attacks can turn developer automation into a data-leak risk, even when the account model itself is still intact.
Researchers have shown that a normal-looking issue on a public repository can become a delivery mechanism for private data exposure when an agentic workflow is allowed to read too broadly.
A prompt-injection finding dubbed GitLost points to a familiar collaboration channel becoming a security boundary: a public issue, an agentic workflow, and private repository data at risk.
A reported browser-editor flaw shows how a single UI mistake can turn a trusted code workspace into a path toward OAuth token theft and private-repo access.
A reported compromise tied to a Visual Studio Code extension shows how a single trusted tool can become a gateway into source-code assets and internal development workflows.
A claimed sale of private GitHub data highlights a familiar danger in modern software security: when repositories, secrets, and automation sit together, one compromise can echo far beyond source code.