registry / @theronap/cortex-mcp / 0.9.280
@theronap/cortex-mcp@0.9.280
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 flagged credential flow is scoped to confidential-brain account verification with the Cortex service, and the flagged launchd artifacts are dormant until explicitly activated. No install-time attack or default persistence behavior was found.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The MCP server checks confidential seats at startup; Codex identity proof is gathered only if seats exist. Antigravity artifacts are written through the explicit cross-editor installer and require manual activation.
Impact
No malicious impact identified in the reviewed source.
Mechanism
The confidential-session flow sends identity proof to the Cortex API for account authorization. The Antigravity plist does not run at load and is not loaded by the adapter.
AI rationale
The flagged credential flow is scoped to confidential-brain account verification with the Cortex service, and the flagged launchd artifacts are dormant until explicitly activated. No install-time attack or default persistence behavior was found.
Network endpoints1
agnoclast.com
Decision evidence
public snapshotAI called this Clean at 93.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json declares no install lifecycle scripts; its scripts are release, promote, and rollback commands.
- The CLI's default branch starts the MCP server; setup and cross-editor wiring use explicit subcommands.
- The confidential-session flow checks for confidential seats first, then gathers Codex identity proof only when seats exist and posts it to the Cortex confidential-session endpoint.
- Antigravity's generated launchd plist has RunAtLoad disabled, and the installer says a separate `launchctl load` is needed to activate it.
Evidence against
- The package reads Codex's OpenAI id_token, which is sensitive, but the source uses it for confidential-brain account proof sent to the Cortex service.
- The Antigravity adapter writes a launchd plist and script when selected by the cross-editor installer, creating dormant persistence artifacts.
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/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@0.9.280.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.280 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.