registry / @theronap/cortex-mcp / 0.9.282
@theronap/cortex-mcp@0.9.282
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged credential flow is tied to a tool call naming a confidential brain and sends proof to the package service. The persistence and configuration writes are setup or self-healing integration behavior; Antigravity's launchd agent is not activated by the package.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The CLI starts the server when invoked without a subcommand; setup and install actions run through their named commands.
Impact
No malicious behavior identified in the inspected flows.
Mechanism
Confidential-session proof goes to the Agnoclast service when a tool call names a confidential brain. The Antigravity installer writes helper files but does not activate its launchd agent.
AI rationale
The manifest has no install lifecycle hook, and the flagged credential flow is tied to a tool call naming a confidential brain and sends proof to the package service. The persistence and configuration writes are setup or self-healing integration behavior; Antigravity's launchd agent is not activated by the package.
Evidence
~/.claude/settings.json~/.cortex/hooks/confidential-guard.mjs~/.cortex/confidential-sessions/<sha256>~/Library/LaunchAgents/com.cortex.antigravity-sync.plist~/.cortex/antigravity-sync.sh
Network endpoints1
agnoclast.com/api/brains/confidential/agent-session
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest declares release, promote, and rollback scripts, with no install lifecycle hook.
- A confidential session is opened only when a tool call names a confidential brain.
- The account proof is sent to the package service's confidential-session endpoint.
- Antigravity wiring writes helper artifacts but does not load the launchd agent.
- The session-start self-heal adds only the package's confidential guard hook to Claude settings.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
6 flaggedlib/capture.mjsView file
1import { readFileSync, accessSync, constants, openSync, mkdirSync } from 'fs'
L2: import { spawn, execFileSync } from 'child_process'
L3: import { homedir } from 'os'
...
L21: if (!res.ok) return null
L22: const j = await res.json().catch(() => ({}))
L23: return Array.isArray(j.types) ? j.types : null
...
L35: try {
L36: if (resolve(String(cwd)) === homedir()) return 'general'
L37: } catch { /* unresolvable path — fall through to basename */ }
...
L45: //
L46: // Handles the four remote forms git emits: scp-like ssh (git@github.com:o/n.git), ssh://, https://,
L47: // git://. The HOST CHECK IS LOAD-BEARING, not cosmetic: this string becomes a clearance key, and
Low
Weak Crypto
Package source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1lib/editors/antigravity.mjsView file
4Trigger-reachable persistence chain: manifest.bin -> bin/cortex-mcp.mjs -> lib/editors/claude.mjs -> lib/editors/index.mjs -> lib/editors/antigravity.mjs
L4: // WatchPaths the trajectory store and runs a one-shot sync. wire() generates the two artifacts
L5: // (the sync.sh + the launchd plist) deterministically. It does NOT run `launchctl load` here
L6: // (an unverifiable system mutation) and it flags the PORTABILITY BLOCKER below.
...
L21: /** The launchd plist, home-substituted. Deterministic — golden-testable byte-for-byte. */
L22: export function renderAntigravityPlist({ home = homedir() } = {}) {
L23: const sh = join(home, '.cortex', 'antigravity-sync.sh')
...
L33: <array>
L34: <string>/bin/bash</string>
L35: <string>${sh}</string>
Findings
4 High3 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/channel.mjs
HighTrigger Reachable Persistencelib/editors/antigravity.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
HighPrevious Version Dangerous Deltalib/confidential_session.mjs
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencelib/editors/antigravity.mjs
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.282.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.282 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.