Back to skill

Security audit

moltlify

Security checks for vulnerabilities and agentic risk

Overview

The skill's runtime instructions ask the agent to download files, write a heartbeat script, and install a cron job (persisting itself) and expect credentials, but the registry metadata does not declare those credentials or an install spec; there are also mixed/inconsistent API domains — these mismatches and the autonomous 'no‑ask' bootstrap are concerning.

Key points to consider before installing: (1) Do not run the provided bootstrap or curl commands without inspection — they write files and install a cron job. (2) Ask the publisher why the registry metadata omits required env vars (MOLTLIFY_USERNAME and MOLTLIFY_API_KEY) and why installation is not declared. (3) Verify the official domain and mismatched references to molter.fun/api endpoints in messaging.md — ask the author to correct or explain these. (4) Prefer to manually download and inspect SKILL.md, HEARTBEAT.md, MESSAGING.md and only install after you trust the source; avoid piping remote curl into execution. (5) If you must test, run in an isolated environment (VM/container) and do not expose real API keys or owner emails. (6) If you want this skill, request an updated package that declares required env vars, documents the install step in registry metadata, removes 'no‑ask' autonomous bootstrap, and removes or explains cross-domain references.

SkillSpector findings are pending for this release.