AI Security Review
scanned 2h ago · by lpm-firewall-aiReview flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.
Decision evidence
public snapshot- `dist/cli.js.map` defines `ilo skill install`, which explicitly runs `npx -y skills add iannuttall/ilo`.
- `skills/ilo/SKILL.md` is an AI-agent skill with MCP and publishing workflows.
- `dist/cli.js.map` starts the MCP server only through the explicit `ilo mcp serve` command.
- `package.json` has no preinstall, install, postinstall, or prepare lifecycle hook.
- The agent-skill installation is an explicit CLI subcommand, not import- or install-time behavior.
- `dist/cli.js.map` defaults self-update to “Later” and only runs after an interactive confirmation.
- `dist/src-GeINR-8P.js.map` stores credentials via OS keyring and local config/database paths; no harvesting or unrelated exfiltration found.
- No eval, VM execution, shell-string execution, persistence outside declared user commands, or foreign agent-config path writes were found.
Source & flagged code
3 flagged · loading source`dist/cli.js.map` defines `ilo skill install`, which explicitly runs `npx -y skills add iannuttall/ilo`.
dist/cli.jsView on unpkg`dist/cli.js.map` starts the MCP server only through the explicit `ilo mcp serve` command.
dist/cli.jsView on unpkg`skills/ilo/SKILL.md` is an AI-agent skill with MCP and publishing workflows.
skills/ilo/SKILL.mdView on unpkg