registry / @markjaquith/agency / 2.73.0

@markjaquith/agency@2.73.0

Manage agentic work across repositories with durable workbases

AI Security Review

scanned 14d ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. npm postinstall installs a package-owned Pi agent extension in the user's Pi extension directory. That extension can augment Pi prompts and expose workbase-local skills when an Agency workbase is active; no network or credential-exfiltration path was found.

Static reason

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

Trigger

npm install, then a Pi agent session in an Agency workbase

Impact

Changes Pi agent behavior for Agency workbases without an explicit setup command.

Mechanism

automatic Pi extension installation and prompt/skill integration

Rationale

The package is not demonstrably malicious, but its postinstall mutates an AI-agent extension surface and changes agent prompts automatically. Per policy, this first-party extension setup warrants a warning rather than a block.

Evidence

package.jsonscripts/install-pi-extension.tspi-extensions/agency.tssrc/services/IntegrationService.tssrc/workbase/opencode-plugin-file.ts~/.pi/agent/extensions/agency.ts

Decision evidence

public snapshot

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

@markjaquith/agency@2.73.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code