registry / @theronap/cortex-mcp / 0.9.119
@theronap/cortex-mcp@0.9.119
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 2mo ago · by lpm-firewall-aiThis is a first-party, explicit-command AI-agent extension with persistent hooks, data transmission, and managed-skill updates. It is a real extension-lifecycle risk, but the absence of automatic lifecycle execution and the explicit setup trigger do not support a malicious verdict.
Static reason
No blocking static signals were detected.
Trigger
The user runs the package's setup or install command; configured agent hooks then run during later sessions.
Impact
The package gains ongoing access to configured agent sessions and can update managed agent skills; no unconsented npm install-time mutation was found.
Mechanism
Persistent AI-agent configuration and session capture.
AI rationale
This is a first-party, explicit-command AI-agent extension with persistent hooks, data transmission, and managed-skill updates. It is a real extension-lifecycle risk, but the absence of automatic lifecycle execution and the explicit setup trigger do not support a malicious verdict.
Evidence
package.jsonbin/cortex-mcp.mjslib/setup.mjslib/editors/claude.mjslib/capture.mjslib/skills.mjslib/editors/antigravity.mjs~/.claude.json~/.claude/settings.json~/.codex/config.toml~/.codex/hooks.json~/.claude/skills/<name>/SKILL.md~/.codex/skills/<name>/SKILL.md~/.cortex/capture.log~/Library/LaunchAgents/com.cortex.antigravity-sync.plist
Network endpoints2
cortex-console.vercel.appcortex-console.vercel.app/api/ingest
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- An explicit setup or install command writes MCP configuration, persistent AI-agent hooks, and permission allow rules.
- The configured capture hook reads AI-session transcript content and sends a redacted payload to the vendor API with the configured token.
- Session-start repair can fetch and overwrite managed skills in Claude Code and Codex directories.
- The package can create an Antigravity launch-agent artifact, although activation requires a separate user command.
Evidence against
- package.json has no preinstall, install, postinstall, or other automatic lifecycle hook.
- The manifest has no dependency on its own package name.
- The control-surface changes require an explicit CLI setup or install action and a token.
- The capture path applies local credential-pattern redaction before its network request.
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'
...
L17: if (!res.ok) return null
L18: const j = await res.json().catch(() => ({}))
L19: return Array.isArray(j.types) ? j.types : null
...
L31: try {
L32: if (resolve(String(cwd)) === homedir()) return 'general'
L33: } catch { /* unresolvable path — fall through to basename */ }
...
L41: //
L42: // Handles the four remote forms git emits: scp-like ssh (git@github.com:o/n.git), ssh://, https://,
L43: // 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
2 High5 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/uninstall.mjs
HighTrigger Reachable Persistencelib/editors/antigravity.mjs
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencelib/editors/antigravity.mjs
MediumAi Review Evidencelib/editors/claude.mjs
MediumAi Review Evidencelib/editors/claude.mjs
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.119.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.119 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.