AI Security Review
scanned 3h ago · by lpm-firewall-aiLPM blocks this version under the AI-agent control-surface policy. The package performs unconsented install-time mutation of a broad/foreign AI-agent control surface. The dropped content is benign-looking, but the postinstall mechanism makes package-supplied skills active in .opencode/skills.
Decision evidence
public snapshot- package.json runs postinstall: node skills/postinstall.js
- skills/postinstall.js creates .opencode/skills in the install cwd
- skills/postinstall.js symlinks or copies package Markdown skill files into that AI-agent skill directory
- Mutation happens automatically during npm install, not by explicit user command
- No network, credential harvesting, child_process, eval, or native/binary loading found
- Runtime lib/tracker.js is an in-memory task/time tracker
- Dropped skill files are project-management prompts without exfiltration or destructive instructions
Source & flagged code
3 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgInstall-time source drops package-supplied AI-agent/MCP control files or instructions.
skills/postinstall.jsView on unpkg · L5