AI Security Review
scanned 6d ago · by lpm-firewall-aiLPM treats this as warn-only first-party agent extension lifecycle risk. The package is a user-invoked AI-context scaffolder that installs OpenCode/AGENTS.md guidance into the current project. This creates a first-party agent-extension lifecycle risk, but no confirmed malicious chain was found.
Decision evidence
public snapshot- `bin/run.mjs` explicitly copies `template/.opencode` into the target project and overwrites `AGENTS.md` after backing it up.
- `template/.opencode/opencode.json` registers `.opencode/plugins/context-loader.js` as an OpenCode plugin.
- `template/.opencode/plugins/context-loader.js` hooks `tool.execute.before`, runs `node scripts/load-context.mjs <task>`, and prepends context output to tool commands.
- `bin/run.mjs` runs `npm install @sentropic/graphify` and several `npx graphify ...` commands during CLI execution.
- `package.json` has no preinstall/install/postinstall lifecycle scripts.
- Behavior is activated by explicit `youmindag`/`npx youmindag` CLI use, not package install or import.
- No credential harvesting, hardcoded exfiltration endpoint, obfuscated payload, remote payload download, persistence, or destructive file deletion found.
- Network use is limited to npm package-manager/Graphify commands and the repository URL in metadata.
Source & flagged code
3 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/run.mjsView on unpkgPackage source invokes a package manager install command at runtime.
bin/run.mjsView on unpkg · L2