registry / @markjaquith/agency / 2.71.26

@markjaquith/agency@2.71.26

Manage agentic work across repositories with durable workbases

AI Security Review

scanned 15d ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. npm postinstall installs a globally loaded Pi agent extension. In an Agency workbase, that extension discovers skills and augments Pi system prompts.

Static reason

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

Trigger

Package installation, followed by a Pi agent start inside an Agency workbase.

Impact

Changes an AI-agent control surface without an explicit setup command, but behavior is limited to the package's own workbase context.

Mechanism

global Pi extension installation and guarded prompt/resource injection

Rationale

This is a concrete install-time mutation of a global agent extension surface, so it warrants a warning. The source shows a first-party, context-guarded extension rather than a malicious exfiltration or remote-execution chain.

Evidence

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

Decision evidence

public snapshot

AI called this Suspicious at 90.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

postinstall invokes the Pi extension installer.

@markjaquith/agency@2.71.26

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code