registry / @astrosheep/keiyaku / 2.9.0

@astrosheep/keiyaku@2.9.0

CLI for running iterative keiyaku workflows with Codex subagents.

AI Security Review

scanned 16h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `keiyaku skills install`, optionally with `--force`.

Impact

Can alter supported agent skill directories only when the user invokes the command; no confirmed covert attack chain.

Mechanism

Explicit agent-skill installation and configured subagent process launching.

Rationale

Source inspection found no lifecycle execution, credential theft, exfiltration, or concealed payload. The explicit agent-skill mutation is a real capability that warrants a warning under the stated policy, but not a block.

Evidence

package.jsonbuild/cli/commands/skills/install/handler.jsbuild/cli/skills-install.jsbuild/agents/opencode-sdk.jsbuild/agents/providers/pi/adapter.jsskills/keiyaku/SKILL.mdskills/keiyaku-akuma/SKILL.md$HOME/.claude/skills/keiyaku$HOME/.agents/skills/keiyaku

Decision evidence

public snapshot

@astrosheep/keiyaku@2.9.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code