> For the complete documentation index, see [llms.txt](https://docs.visdom.virtuslab.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.visdom.virtuslab.com/visdom-security/visdom-security.md). # Visdom Security Contain the agent while it works, harden what it ships. An autonomous agent is an unattended process holding your credentials, with network access, acting on instructions it reads from your repository. Everything in this component follows from taking that sentence literally. ## What changes when the author is an agent **Prompt injection is a supply chain now.** Instructions can hide anywhere the agent reads: a README, a dependency's changelog, an issue comment, a documentation page. An agent that follows instructions faithfully will follow those too. **Credentials leak at machine speed.** Secrets have always leaked into commits. The difference is throughput, and that an agent has no instinct that a token in a log line is a problem. **Dependencies drift into fiction.** A meaningful share of packages a model recommends do not exist. Somebody registers the plausible name, and the typo becomes an install. **Insecure by default, at scale.** Models reproduce the patterns they were trained on, including the vulnerable ones, and they do it consistently rather than occasionally. None of this is exotic. It is the ordinary set of problems, arriving faster, from an actor with credentials and no judgement. ## Two layers **Containment** puts the agent inside a boundary it does not control, and never hands it the real secrets. **Continuous AppSec** scans everything it produces before that reaches production, with the noise filtered down to what is actually reachable. The first assumes the agent will be tricked. The second assumes some of what it writes will be wrong. Neither trusts the model to behave. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.visdom.virtuslab.com/visdom-security/visdom-security.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.