registry / @dat999zx/knowl / 1.1.0

@dat999zx/knowl@1.1.0

A Knowledge Operating System for AI Agents

AI Security Review

scanned 21h ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. No install-time attack surface is present. Explicit `knowl init` configures project agent integrations and hooks that inject local knowledge context; explicit skill execution can run project-owned scripts.

Static reason

No blocking static signals were detected.; previous stored version diff introduced dangerous source

Trigger

User runs `knowl init` or `knowl skill run`.

Impact

Can influence configured AI-agent sessions and execute selected project skill content.

Mechanism

Explicit project-local MCP/hook setup and user-invoked skill execution.

Rationale

This is a user-invoked AI-agent extension with hook-based control of configured project sessions and executable skill support. Its behavior is package-aligned and not block-worthy, but warrants a warning under the agent-extension policy.

Evidence

package.jsondist/index.jsdist/chunk-IVC2P6FU.jsAGENTS.md.gitignore.knowl/config.json.knowl/skills/<name>/.codex/config.toml.codex/hooks.json.claude/settings.local.json.cursor/mcp.json.cursor/hooks.json

Network endpoints2

localhost:11434/v1127.0.0.1

@dat999zx/knowl@1.1.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code