aptly@0.1.21
Model and reasoning recommendations for subagents, powered by the OpenAI Decisions API.
AI security review
scanned · by lpm-firewall-aiThe reachable postinstall modifies existing coding-agent settings by registering the package’s MCP server and adding its own hook, which warrants a warning under the agent extension lifecycle rule. The inspected network request sends the configured key to OpenAI’s Decisions API for the package’s stated function; I found no concrete malicious behavior.