onesignal-setup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited onesignal-setup (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Help the user connect Cursor to OneSignal through the hosted OneSignal MCP server.
This plugin uses OAuth through the hosted OneSignal MCP server.
The user needs:
Tell users to follow Cursor's OAuth prompt for the OneSignal MCP server. Never ask users to paste OAuth tokens, API keys, private keys, or credentials into chat, source files, rules, skills, commits, screenshots, or issue reports.
If Cursor was already open when the plugin was installed or updated, ask the user to reload Cursor with Developer: Reload Window or fully restart Cursor.
Use a read-only or utility MCP tool first. Prefer:
onesignal_healthonesignal_configonesignal_reference_overviewDo not start with message sends, segment updates, template updates, Journey creation, exports, or subscription transfers.
If tools do not appear:
~/.cursor/plugins/local/onesignal..cursor-plugin/plugin.json is at the plugin root.mcp.json has a top-level mcpServers object.If tools appear but calls fail:
https://api.onesignal.com/mcp/oauth.For any write or send operation:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.