registry / @andy-toolforge/knowledge-base / 0.1.1

@andy-toolforge/knowledge-base@0.1.1

Filesystem-first knowledge base facade for AI agents: JSON store with CRUD/search, optional best-effort Supermemory/Serena adapters, and a management skill installed into client projects.

AI Security Review

scanned 3h ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. Installation mutates the client project's OpenCode skill directory without an explicit user command. This is a foreign AI-agent control-surface write.

Static reason

One or more suspicious static signals were detected.

Trigger

npm install

Impact

A package-installed skill can influence OpenCode agent behavior in the client project.

Mechanism

postinstall installs an AI-agent skill into .opencode/skills

Policy narrative

During npm installation, the package runs a postinstall helper that installs its management skill. Its documentation identifies the destination as the client project's .opencode/skills directory, an AI-agent control surface, without requiring a separate user setup command.

Rationale

This is a concrete unconsented postinstall mutation of a foreign AI-agent control surface. The absence of exfiltration does not remove that install-time control-surface risk. Product guard normalized a concrete AI-agent control hijack publish_block to the blockable dangerous-capability shape.

Evidence

package.jsonskills/postinstall.jsREADME.mdskills/knowledge-base-management.md.opencode/skills/knowledge-base-*

Decision evidence

public snapshot

AI identified this as a dangerous AI-agent capability at 94.0% confidence with false-positive risk.

@andy-toolforge/knowledge-base@0.1.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code