registry / @theronap/cortex-mcp / 0.9.229
@theronap/cortex-mcp@0.9.229
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 23d ago · by lpm-firewall-aiThe automatic first-party MCP permission migration is a concrete agent configuration capability, so it warrants a warning. No malicious behavior or npm install-time trigger was identified.
Static reason
No blocking static signals were detected.
Trigger
A Claude session starts with the package's skills hook installed and the existing MCP entry still under the old key.
Impact
The renamed package tools can run without permission prompts after the migration.
Mechanism
The migration adds missing package tool rules to Claude settings, verifies them, then changes the existing MCP entry to the new key.
AI rationale
The automatic first-party MCP permission migration is a concrete agent configuration capability, so it warrants a warning. No malicious behavior or npm install-time trigger was identified.
Evidence
lib/skills.mjslib/migrate_key.mjslib/editors/claude.mjs~/.claude/settings.json~/.claude.json
Decision evidence
public snapshotAI called this Suspicious at 83.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- package.json exposes a CLI and lists only release, promote, and rollback scripts; it has no npm install hook.
- The skills session-start path calls a migration that only proceeds when the existing Claude config contains this package under its old key.
- When needed, the migration writes allow rules for the new package namespace before switching the config key. Those rules are generated from the package's named MCP tool list.
- The other flagged locations describe editor configuration, managed skills, uninstall, and transcript lookup. The Antigravity artifacts are written through the explicit install flow and are not loaded automatically.
Evidence against
- The migration preserves a guarded migration path for the package's own MCP namespace; the inspected code does not show a change to unrelated agent commands.
- The Antigravity adapter warns that activation requires a manual launchctl command and that its sync depends on a local development checkout.
Behavioral surface
ChildProcessCryptoEnvironmentVars
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 High4 Medium5 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
MediumSuspicious Lifecycle Evidencepackage.json
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.229.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.229 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.