registry / @theronap/cortex-mcp / 0.9.120
@theronap/cortex-mcp@0.9.120
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-aiThe source implements an explicit-user-command agent extension that persists hooks and transmits session-derived content to its named service. It is not malicious under the install-control policy, but its ongoing editor control surface warrants a warning.
Static reason
No blocking static signals were detected.
Trigger
The user runs cortex-mcp setup or cortex-mcp install, then uses a configured editor.
Impact
Session content and prompts may leave the machine, and configured hooks run on future editor events.
Mechanism
User-authorized AI editor configuration, hooks, and authenticated context ingestion.
AI rationale
The source implements an explicit-user-command agent extension that persists hooks and transmits session-derived content to its named service. It is not malicious under the install-control policy, but its ongoing editor control surface warrants a warning.
Evidence
package.jsonlib/editors/claude.mjslib/editors/codex.mjslib/editors/antigravity.mjslib/capture.mjslib/hydrate.mjslib/diagnose.mjs~/.claude.json~/.claude/settings.json~/.codex/config.toml~/.codex/hooks.json~/.cortex/antigravity-sync.sh~/Library/LaunchAgents/com.cortex.antigravity-sync.plist
Network endpoints2
cortex-console.vercel.app/api/ingestcortex-console.vercel.app/api/session-context
Decision evidence
public snapshotAI called this Suspicious at 92.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- Explicit setup writes MCP configuration and recurring editor hooks.
- The Stop hook reads session transcripts and posts an authenticated session digest; it can fall back to sending transcript text.
- The prompt hook sends a redacted user prompt to the service.
- The optional Antigravity adapter writes a launch-agent artifact, though it does not activate it.
Evidence against
- package.json has no preinstall, install, or postinstall hook.
- These changes require an explicit setup or install command.
- The service endpoint is package-aligned and token-authenticated.
- No hidden payload, credential theft, destructive action, or foreign configuration mutation was confirmed.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
6 flaggedlib/capture.mjsView file
318// Redact credential-shaped strings BEFORE anything leaves the machine — this `transcript`
// feeds local edge/typed extraction AND the fallback POST to the org. A secret in a
// transcript (pasted key, a tool that read a config file, a token inlined in a hook cmd)
// must never be transmitted or stored. See redact.mjs.
const transcript = hook.transcript_path ? redactSecrets(transcriptTail(hook.transcript_path)) : ''
Medium
Ai Review Evidence
The Stop hook reads session transcripts and posts an authenticated session digest; it can fall back to sending transcript text.
lib/capture.mjsView on unpkg · L3181import { 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 · L1Findings
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/capture.mjs
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.120.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.120 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.