registry / @theronap/cortex-mcp / 0.9.164
@theronap/cortex-mcp@0.9.164
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 package has no npm lifecycle hook that activates the Antigravity setup. Its explicit installer can create launchd persistence artifacts, so this warrants a warning as a guarded agent extension capability rather than a block.
Static reason
No blocking static signals were detected.
Trigger
A user runs the package's install command and selects or detects Antigravity; the watcher requires a separate load action.
Impact
If activated, the watcher can run the sync script when its watched Antigravity path changes; the source also says the script depends on a local development checkout.
Mechanism
The adapter writes a sync script and launchd plist into the user's home directory and prints instructions to load the plist.
AI rationale
The package has no npm lifecycle hook that activates the Antigravity setup. Its explicit installer can create launchd persistence artifacts, so this warrants a warning as a guarded agent extension capability rather than a block.
Evidence
lib/editors/antigravity.mjsbin/cortex-mcp.mjs
Decision evidence
public snapshotAI called this Suspicious at 87.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest has no preinstall, install, or postinstall hook; it exposes a command-line entrypoint.
- The Antigravity integration is reached through the explicitly invoked install command, which wires detected editors.
- Antigravity setup writes a sync script and launchd plist under the user's home directory, then tells the user to load the plist to activate it.
- Codex and Cursor wiring requires a token; their adapters merge the package's MCP entry into editor configuration.
- The skills module targets Claude Code and Codex skill directories; uninstall has a dry-run option and removes managed wiring.
- The diagnosis helper includes an environment-only token resolver; its source does not establish an unrelated credential recipient.
Evidence against
- The Antigravity integration creates a launchd configuration and executable sync script, so it has a guarded persistence capability.
- The package manifest does not show an automatic npm lifecycle trigger for that setup.
Behavioral surface
ChildProcessCrypto
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 Limitedlib/diagnose.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@0.9.164.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.164 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.