registry / @markjaquith/agency / 3.2.8

@markjaquith/agency@3.2.8

Manage agentic work across repositories with durable workbases

AI Security Review

scanned 6h ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. Installing the package automatically places its Agency Pi extension in the user's global Pi extension directory. The extension affects later Pi sessions by discovering project skill paths and adding workbase instructions to their prompts.

Static reason

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

Trigger

npm installation runs the postinstall hook; a later Pi agent session activates the extension.

Impact

Future Pi sessions can load project-controlled skills and instructions when Agency workbase context is detected.

Mechanism

Automatic global Pi extension installation and agent lifecycle prompt augmentation.

Rationale

The automatic postinstall mutation of a global agent extension surface warrants a warning. The source shows a bounded first-party extension setup rather than a concrete malicious chain.

Evidence

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

Decision evidence

public snapshot

AI called this Suspicious at 94.0% confidence as Dangerous Capability with low false-positive risk.

Evidence for warning

The postinstall lifecycle hook automatically runs an extension installer.

@markjaquith/agency@3.2.8

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code