registry / @theronap/cortex-mcp / 0.9.154
@theronap/cortex-mcp@0.9.154
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 flagged persistence is created by an explicit editor setup command and is not activated automatically. I classify this as a warning for guarded agent extension lifecycle behavior, with no confirmed malicious chain.
Static reason
No blocking static signals were detected.
Trigger
A user runs the install command with Antigravity selected or detected, then separately loads the generated launchd plist.
Impact
If activated and the local checkout exists, the watcher can run the configured sync operation after watched storage changes.
Mechanism
The adapter writes a shell script and watcher plist; the script invokes with-token and a sync command from a local checkout.
AI rationale
The flagged persistence is created by an explicit editor setup command and is not activated automatically. I classify this as a warning for guarded agent extension lifecycle behavior, with no confirmed malicious chain.
Evidence
lib/install.mjslib/editors/antigravity.mjs~/Library/LaunchAgents/com.cortex.antigravity-sync.plist~/.cortex/antigravity-sync.sh
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- package.json defines release, promote, and rollback scripts; it has no npm install lifecycle hook.
- The explicit install command calls each selected editor adapter’s wire function.
- The Antigravity adapter writes a shell script and LaunchAgents plist; its plist watches Antigravity’s global storage and can run that script when activated.
- The generated script invokes the package’s with-token command and a local checkout’s sync command.
- The Codex and Cursor excerpts identify editor adapters; setup, skills, and uninstall excerpts identify their corresponding configuration paths.
Evidence against
- Antigravity’s wire function says it does not load the launchd job; activation requires a separate user command.
- The generated Antigravity artifacts are first-party setup behavior, and the source warns that the local checkout dependency prevents portable operation.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
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@0.9.154.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.154 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.