The generated skills expose the workspace token to the selected agent context, creating a concrete but conditional credential exposure that warrants a warning. The source does not establish covert transfer to an unrelated recipient or justify blocking publication.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
A Cursor workspace message reaches the agent spawn flow, or a Claude adapter configured for skills mode builds a command.
Impact
The agent can use the token for workspace API access, and the token may be disclosed to the selected provider through its context. The source does not establish disclosure to an unrelated package-selected server.
Mechanism
The skill includes the token in an authorization header and instructs the agent to run workspace API commands. A loaded skill can place the token in context sent to the selected agent provider.
Evidence
src/adapters/base.jssrc/adapters/workspace-prompt.jssrc/adapters/cursor.jssrc/adapters/claude.js
Network endpoints1
workspace-endpoint.openagents.org