The inspected source supports a first-party agent skill deployment capability, guarded by a saved setting that defaults off. Under the agent integration policy, this warrants a warning; the source does not establish a concrete attack.
Static reason
One or more suspicious static signals were detected.; source matched previously finalized malicious package; routed for review; previous stored version diff introduced dangerous source
Trigger
An agent connection can request automatic reconciliation when the saved autoSyncProjectGroups setting is enabled; saving settings can also schedule a group sync.
Impact
The operation can change agent skill files and thereby affect later agent behavior. The inspected source does not establish malicious content or unconsented activation.
Mechanism
The server prepares skill file write operations and sends them to a connected agent for application in configured skill directories.
Evidence
standalone/.next/server/chunks/_1c4_xnyuf9e7t._.js.claude/skills.cursor/skills.copilot/skills.codex/skills