registry / @theronap/cortex-mcp / 0.9.200
@theronap/cortex-mcp@0.9.200
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-aiSource inspection shows explicitly invoked onboarding, followed by automatic package updates and organization-skill installation in configured assistants. That creates a guarded agent extension lifecycle risk, but no concrete attack or unconsented install-time mutation was established.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
A user runs login, setup, or install; later, a configured assistant invokes its skills-repair hook.
Impact
Later package releases and organization skills can affect assistant behavior after setup. Source inspection does not establish credential theft, a foreign control-surface mutation, or malicious payload behavior.
Mechanism
Setup uses a moving package release tag for assistant configuration. Skill repair fetches organization-published skills with the Cortex token and installs them into detected assistant skill directories.
AI rationale
Source inspection shows explicitly invoked onboarding, followed by automatic package updates and organization-skill installation in configured assistants. That creates a guarded agent extension lifecycle risk, but no concrete attack or unconsented install-time mutation was established.
Evidence
lib/setup.mjslib/skills.mjsbin/cortex-mcp.mjspackage.jsonlib/editors/codex.mjslib/editors/cursor.mjslib/uninstall.mjslib/working_files.mjslib/editors/antigravity.mjslib/capture.mjs
Decision evidence
public snapshotAI called this Suspicious at 79.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes a CLI and defines no install lifecycle hook.
- Setup receives a token through the CLI and writes assistant configuration only when invoked.
- The Codex and Cursor adapters require a token before wiring their assistant configurations.
- Org skills are fetched with the Cortex token, then installed into detected assistant skill directories; setup describes skills as part of onboarding.
- Setup configures a moving package release tag, so wired assistants can receive later releases when they launch.
- Capture sends ingest data through the Cortex API path; inspected source does not establish a separate credential recipient.
Evidence against
- An explicit setup or install action can configure assistant integrations and enable later package updates.
- Session-start skill repair can install organization-published skill content into assistant skill directories.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
Source & flagged code
6 flaggedlib/capture.mjsView file
•matchType = previous_version_dangerous_delta
matchedPackage = @theronap/cortex-mcp@0.9.150
matchedIdentity = npm:QHRoZXJvbmFwL2NvcnRleC1tY3A:0.9.150
similarity = 0.761
summary = stored previous version shares package body but lacks this dangerous source file
High
Previous Version Dangerous Delta
This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
lib/capture.mjsView on unpkg1import { 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.mjs
Findings
4 High3 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/uninstall.mjs
HighTrigger Reachable Persistencelib/editors/antigravity.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
HighPrevious Version Dangerous Deltalib/capture.mjs
MediumNetwork
MediumEnvironment Vars
MediumInstall Persistencelib/editors/antigravity.mjs
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.200.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.200 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.