registry / @theronap/cortex-mcp / 0.9.226
@theronap/cortex-mcp@0.9.226
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 25d ago · by lpm-firewall-aiThe source does not establish malicious behavior or an install-time attack. The only reviewed control-surface mutation is an explicit uninstall action limited to package-managed configuration, so no confirmed attack surface remains.
Static reason
No blocking static signals were detected.
Trigger
A user explicitly invokes the uninstall command.
Impact
It can remove this package’s agent wiring and skills, but the inspected behavior does not show broader configuration changes or an automatic install-time trigger.
Mechanism
The command removes recognized Cortex MCP entries, hooks, and named skills from the user’s agent configuration locations; file writes are backed up and can be previewed with dry-run.
AI rationale
The source does not establish malicious behavior or an install-time attack. The only reviewed control-surface mutation is an explicit uninstall action limited to package-managed configuration, so no confirmed attack surface remains.
Evidence
lib/uninstall.mjsbin/cortex-mcp.mjs
Decision evidence
public snapshotAI called this Clean at 81.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes a command-line entrypoint and declares no install lifecycle hook.
- Uninstall runs only when its explicit command is dispatched; it removes managed MCP entries and hooks, and backs up files before writing.
- The uninstaller also removes named Cortex skills from the Claude and Codex skill directories.
- The editor adapters target the package’s named Cortex integrations; the Codex and Cursor adapters only wire when a token is supplied.
- The Antigravity adapter detects its application state and describes generated sync artifacts; its source says it does not load the launch agent itself.
Evidence against
- The inspected source does not show an automatic install-time mutation or an unrelated agent configuration being added by uninstall.
- Uninstall supports a dry-run and filters for managed integrations, limiting its configuration changes.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
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/install.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
3 High3 Medium6 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/uninstall.mjs
HighTrigger Reachable Persistencelib/editors/antigravity.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencelib/editors/antigravity.mjs
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.226.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.226 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.