Margin Editor ↗
Margin Editor is an officially published WebMCP tool from OpenAI. Anomity scores its risk at 10 out of 100 (low).
Analysis summary
Margin Editor is an officially published WebMCP tool from OpenAI. Anomity scores its risk at 10 out of 100 (low).
A local note editor in which the agent has its own identity: it creates notes and responds in the margin as a distinct participant rather than silently editing the user's text. A deliberate demonstration that agent-native does not have to mean agent-invisible.
That identity separation is the interesting security property. When agent output is attributable and spatially separated from human content, prompt-injected text the agent produces is visibly the agent's, not the user's — which matters enormously for documents that later feed other systems. Declared capabilities are browser control and outbound network access. It is catalogued as the design pattern worth copying: mark what the model wrote.
Why this entry scored 10 out of 100
This profile starts at the catalog's neutral base of 50. Because the entry is officially published, trust adjusts the score by -40. The entry declares no high-risk capabilities on its own, so capabilities add nothing. It matches no dangerous capability combinations. The clamped result is 10, placing it in the low band.
Findings
-
Published by the vendor Trust offset
Capabilities
Every capability the entry declares, with the security implication of each.
-
browser:controlBrowser controlDrives a browser session. Combined with credential access can impersonate the user on web services. -
network:outboundOutbound networkCan make outbound network requests. Required for hosted model providers and remote APIs; also the path for data exfiltration if combined with read access.