registry / @cursor/july / 0.2.14

@cursor/july@0.2.14

Build, test, and deploy BDK bots and agents as code on Cursor's agent harness.

AI Security Review

scanned 10h ago · by lpm-firewall-ai

LPM treats this as warn-only first-party agent extension lifecycle risk. The package performs guarded agent integration setup: its npm postinstall copies its own skills into the user’s Cursor skills directory, and Slack session setup can add a package-owned hook to a harness workspace.

Static reason

High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review

Trigger

npm installation triggers the skill copy; a Slack session with a continuation key and steering disabled triggers carrier installation.

Impact

These actions alter agent behavior through package-owned skills and hooks. The inspected source does not establish credential theft or another active attack.

Mechanism

The install helper copies shipped skills into the user’s Cursor skills directory. The carrier writes workspace files and adds a command to Cursor pre-tool and post-tool hooks.

AI rationale

The source shows package-owned skills and a conditional Slack hook carrier changing agent configuration. This warrants a warning for guarded agent integration setup, but the inspected behavior does not establish a concrete malicious attack.

Evidence

package.jsondist/internal/install-cursor-skills.jsdist/internal/session-engine.jsdist/channels/slack/nudge-carrier.js

Decision evidence

public snapshot

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

@cursor/july@0.2.14

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Affected versions and remediation

Source & flagged code