Skip to content

Define input-length mitigations in code points #265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
HaoChiBao wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Define input-length mitigations in code points #265

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions index.bs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1775,11 +1775,11 @@ respective private browsing modes are safely exposed to [=agents=] and that thes

<h4 id="mitigation-restrict-input-lengths">Restricting maximum input lengths</h4>

**What:** Restrict the maximum amount of characters
**What:** Restrict the maximum number of code points

**Threats addressed:** [[#metadata-description-attacks]]

**How:** This restriction would not fully solve prompt injection attacks but helps shrink the possible universe of attacks, preventing longer prompts that leverage e.g. repetition and sockpuppetting [[SOCKPUPPETTING]] to convince agents of malicious tasks. The specification already implements a nominal size restriction of 128 characters for the tool {{ModelContextTool/name}} (see [[#supporting-concepts]]), but further work is needed to evaluate the right size limits for titles, names, and other inputs. See [Issue #73](https://github.com/webmachinelearning/webmcp/issues/73).
**How:** This restriction would not fully solve prompt injection attacks but helps shrink the possible universe of attacks, preventing longer prompts that leverage e.g. repetition and sockpuppetting [[SOCKPUPPETTING]] to convince agents of malicious tasks. The specification already implements a nominal size restriction of 128 ASCII [=code points=] for the tool {{ModelContextTool/name}} (see [[#supporting-concepts]]), but further work is needed to evaluate the right size limits for titles, names, and other inputs. See [Issue #73](https://github.com/webmachinelearning/webmcp/issues/73).

<h4 id="mitigation-shared-attack-evals">Supporting interoperable probabilistic defense structures through shared attack eval datasets</h4>

Expand Down
Loading