registry / @markjaquith/agency / 3.2.12

@markjaquith/agency@3.2.12

Manage agentic work across repositories with durable workbases

AI Security Review

scanned 3h ago · by lpm-firewall-ai

LPM flags this version as an AI-agent control-surface risk. Installing the package automatically adds a global Pi agent extension. That extension changes agent resources and system prompts for matching workbases.

Static reason

One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source

Trigger

npm postinstall

Impact

A package install changes a separate AI-agent control surface without an explicit user command.

Mechanism

Global Pi extension installation and agent prompt modification

Policy narrative

During npm postinstall, the package copies its extension to the user's global Pi agent extension directory. When Pi later starts in a matching workbase, that extension exposes skill directories and appends workbase instructions to the agent system prompt. This is an unconsented install-time mutation of a broad AI-agent control surface.

Rationale

The automatic postinstall writes and activates code in Pi's user-wide extension location, then alters agent context and prompts. This meets the install-control-surface block policy despite no observed exfiltration.

Evidence

package.jsonscripts/install-pi-extension.tspi-extensions/agency.ts~/.pi/agent/extensions/agency.ts

Decision evidence

public snapshot

AI identified this as a dangerous AI-agent capability at 98.0% confidence with false-positive risk.

@markjaquith/agency@3.2.12

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code