registry / @theronap/cortex-mcp / 0.9.116
@theronap/cortex-mcp@0.9.116
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-aiNo npm lifecycle script performs automatic mutation, and no concrete malicious chain is shown. The package nevertheless creates persistent editor hooks and remotely refreshed agent skills after an explicit setup command, so it should warn rather than block.
Static reason
No blocking static signals were detected.
Trigger
The user runs cortex-mcp setup, install, or repair; installed editor hooks then run on agent events.
Impact
The service can receive session-derived content and dynamically supply skills that affect later agent behavior.
Mechanism
User-authorized AI-editor wiring with session capture and remote skill synchronization.
AI rationale
No npm lifecycle script performs automatic mutation, and no concrete malicious chain is shown. The package nevertheless creates persistent editor hooks and remotely refreshed agent skills after an explicit setup command, so it should warn rather than block.
Evidence
package.jsonbin/cortex-mcp.mjslib/setup.mjslib/editors/claude.mjslib/editors/codex.mjslib/capture.mjslib/skills.mjslib/diagnose.mjs~/.claude.json~/.claude/settings.json~/.codex/config.toml~/.codex/hooks.json~/.claude/skills~/.codex/skills~/.cortex
Network endpoints3
cortex-console.vercel.appcortex-console.vercel.app/api/ingestcortex-console.vercel.app/api/skills
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The explicit setup command writes MCP configuration and recurring hooks into Claude and Codex user configuration.
- The installed Stop hook reads session transcript content and posts a derived summary or fallback transcript to the package service.
- A recurring SessionStart hook can fetch organization-provided skills and install them into detected agent skill directories.
- The package service endpoint defaults to cortex-console.vercel.app.
Evidence against
- package.json has no preinstall, install, postinstall, or prepare lifecycle hook.
- Configuration changes occur only through CLI setup, install, or repair paths, not package installation.
- Capture redacts credential-shaped strings before transcript data is sent.
- No source evidence shows covert exfiltration, destructive behavior, or foreign control-surface mutation during npm installation.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
Source & flagged code
6 flaggedlib/capture.mjsView file
406let res
try {
// Best-effort background ingest: bound it tight and retry once so a hanging/504-ing server
// makes a DETACHED worker self-terminate in ~20s instead of lingering on 3 unbounded attempts.
res = await fetchCortex(`${base}/api/ingest`, {
method: 'POST',
headers: { Authorization: `Bearer ${token}`, 'Content-Type': 'application/json' },
body: JSON.stringify(ingestBody),
timeoutMs: 10_000,
}, { retries: 1 })
Medium
Ai Review Evidence
The installed Stop hook reads session transcript content and posts a derived summary or fallback transcript to the package service.
lib/capture.mjsView on unpkg · L4061import { 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/setup.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@0.9.116.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.116 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.