registry / @mystilleef/pi-subagent / 0.12.0

@mystilleef/pi-subagent@0.12.0

Pi subagent for the SPAE Framework

AI Security Review

scanned 9h 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 /run command or a host agent invoking the registered subagent tool.

Impact

Child agents may use their configured tools and inherited environment in the active workspace.

Mechanism

spawns approved child pi processes using discovered agent configuration

Rationale

The package is not malicious by source evidence, but it intentionally enables approved nested agent execution with inherited environment, a dangerous dual-use capability warranting a warning.

Evidence

package.jsonsrc/index.tssrc/child/process.tssrc/shared/utils.tssrc/agent/agents.tssrc/child/prompt-setup.ts/tmp/pi-subagent-*/prompt-*.md

Decision evidence

public snapshot

AI called this Suspicious at 91.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

@mystilleef/pi-subagent@0.12.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code