@dharma-ai-labs/agent-fabric@0.2.226
Local-first CLI for connecting coding agents to Dharma evaluation, orchestration, and signed Skill delivery
AI security review
scanned · by lpm-firewall-aiThe runtime skill activation path changes an AI agent's permission settings without requiring a user command for that activation. Although the added permission is narrowly scoped and documented, the package rules treat automatic permission-setting changes as AI-agent control hijacking.