Repository navigation
Conversation
domfarolino
approved these changes
Oct 8, 2026
domfarolino
left a comment
domfarolino
left a comment
Collaborator
There was a problem hiding this comment.
This looks good. It'd be great to hear from @npdoty too—how do you feel about this?
|
|
||
| These capabilities enable powerful user experiences but also create new risks that must be addressed through a combination of protocol design, agent implementation, and user controls. | ||
|
|
||
| Many of the risks associated with these baseline capabilities—such as indirect prompt injection from untrusted web content, cross-origin data correlation, and unauthorized actions within an authenticated session—apply broadly to any [=agent=] operating on the web on a user's behalf, regardless of whether a site exposes WebMCP tools. While WebMCP provides protocol-level boundaries and semantic hints ({{ToolAnnotations/readOnlyHint}}, {{ToolAnnotations/consequentialHint}}, {{ToolAnnotations/untrustedContentHint}}), a malicious site can omit or misrepresent those hints. Preventing an [=agent=] from being manipulated by an untrusted site or inappropriately disclosing cross-origin data is primarily the responsibility of the [=agent=]'s own security model rather than something a single web API specification can normatively enforce. Broader standardization and guidance around [=agent=] permissions, delegation, and web interactions are being explored in the proposed [Agentic Web Working Group](https://w3c.github.io/charter-drafts/2026/agenticweb-wg.html) [[AGENTICWEB-WG]]. |
Collaborator
There was a problem hiding this comment.
Can you wrap this (possibly using the https://github.com/domfarolino/specfmt crate) to 100 characters per line? Some of the pre-existing lines in the spec predate that formatting requirement which I should fix separately. But if we could break this up to match all of the new stuff that'd be great! If you see the stack of comments below, and note how they're not anchored to the line that they concern, you'll see why we have the column length guideline.
|
|
||
| These capabilities enable powerful user experiences but also create new risks that must be addressed through a combination of protocol design, agent implementation, and user controls. | ||
|
|
||
| Many of the risks associated with these baseline capabilities—such as indirect prompt injection from untrusted web content, cross-origin data correlation, and unauthorized actions within an authenticated session—apply broadly to any [=agent=] operating on the web on a user's behalf, regardless of whether a site exposes WebMCP tools. While WebMCP provides protocol-level boundaries and semantic hints ({{ToolAnnotations/readOnlyHint}}, {{ToolAnnotations/consequentialHint}}, {{ToolAnnotations/untrustedContentHint}}), a malicious site can omit or misrepresent those hints. Preventing an [=agent=] from being manipulated by an untrusted site or inappropriately disclosing cross-origin data is primarily the responsibility of the [=agent=]'s own security model rather than something a single web API specification can normatively enforce. Broader standardization and guidance around [=agent=] permissions, delegation, and web interactions are being explored in the proposed [Agentic Web Working Group](https://w3c.github.io/charter-drafts/2026/agenticweb-wg.html) [[AGENTICWEB-WG]]. |
Collaborator
There was a problem hiding this comment.
Let's start a new paragraph starting with "Preventing an [=agent=] [...]"
|
|
||
| These capabilities enable powerful user experiences but also create new risks that must be addressed through a combination of protocol design, agent implementation, and user controls. | ||
|
|
||
| Many of the risks associated with these baseline capabilities—such as indirect prompt injection from untrusted web content, cross-origin data correlation, and unauthorized actions within an authenticated session—apply broadly to any [=agent=] operating on the web on a user's behalf, regardless of whether a site exposes WebMCP tools. While WebMCP provides protocol-level boundaries and semantic hints ({{ToolAnnotations/readOnlyHint}}, {{ToolAnnotations/consequentialHint}}, {{ToolAnnotations/untrustedContentHint}}), a malicious site can omit or misrepresent those hints. Preventing an [=agent=] from being manipulated by an untrusted site or inappropriately disclosing cross-origin data is primarily the responsibility of the [=agent=]'s own security model rather than something a single web API specification can normatively enforce. Broader standardization and guidance around [=agent=] permissions, delegation, and web interactions are being explored in the proposed [Agentic Web Working Group](https://w3c.github.io/charter-drafts/2026/agenticweb-wg.html) [[AGENTICWEB-WG]]. |
Collaborator
There was a problem hiding this comment.
Let's replace "a single web API specification" with "this specification". Because who knows, maybe we'll come up with a single "secure web agent harness" specification 🤷♂️ .
|
|
||
| These capabilities enable powerful user experiences but also create new risks that must be addressed through a combination of protocol design, agent implementation, and user controls. | ||
|
|
||
| Many of the risks associated with these baseline capabilities—such as indirect prompt injection from untrusted web content, cross-origin data correlation, and unauthorized actions within an authenticated session—apply broadly to any [=agent=] operating on the web on a user's behalf, regardless of whether a site exposes WebMCP tools. While WebMCP provides protocol-level boundaries and semantic hints ({{ToolAnnotations/readOnlyHint}}, {{ToolAnnotations/consequentialHint}}, {{ToolAnnotations/untrustedContentHint}}), a malicious site can omit or misrepresent those hints. Preventing an [=agent=] from being manipulated by an untrusted site or inappropriately disclosing cross-origin data is primarily the responsibility of the [=agent=]'s own security model rather than something a single web API specification can normatively enforce. Broader standardization and guidance around [=agent=] permissions, delegation, and web interactions are being explored in the proposed [Agentic Web Working Group](https://w3c.github.io/charter-drafts/2026/agenticweb-wg.html) [[AGENTICWEB-WG]]. |
Collaborator
There was a problem hiding this comment.
Let's add "identity" to the list of things the agentic WG is handling.
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Clarifies in Section 6.2 that general agentic browsing risks (such as indirect prompt injection from untrusted web content and cross-origin data correlation) apply broadly to agents operating on the web and require agent-level security models beyond what a single web API specification can normatively enforce.
Adds an Agent-Level Guardrails and Best Practices subsection in Section 6.4 (Mitigations) noting that agents cannot rely solely on site-asserted tool descriptions or annotations and linking out to external implementation guidance (Agent security considerations for WebMCP and Secure tools with WebMCP), as well as the proposed W3C Agentic Web Working Group Charter where broader cross-ecosystem agent policies and constraints are being explored.
Related to #313.
Preview | Diff