registry / @theronap/cortex-mcp / 0.9.232
@theronap/cortex-mcp@0.9.232
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 20d ago · by lpm-firewall-aiThe source shows a user-enabled, first-party agent skill update capability with automatic refreshes, so a warning is appropriate. The package does not establish a concrete malicious attack or an install-time trigger.
Static reason
No blocking static signals were detected.
Trigger
A user runs setup or install; afterward, Claude Code session start runs skill repair.
Impact
Updated instructions may influence how the agent behaves in later sessions.
Mechanism
The package fetches organization skills from its API and writes the returned markdown into agent skill directories without asking for approval of each update.
AI rationale
The source shows a user-enabled, first-party agent skill update capability with automatic refreshes, so a warning is appropriate. The package does not establish a concrete malicious attack or an install-time trigger.
Evidence
lib/setup.mjslib/editors/claude.mjslib/skills.mjs~/.claude/skills/<name>/SKILL.md~/.codex/skills/<name>/SKILL.md
Network endpoints1
agnoclast.com/api/skills
Decision evidence
public snapshotAI called this Suspicious at 82.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest exposes a CLI and has no npm install lifecycle hook; setup and install run through explicit CLI commands.
- Setup installs bundled skills and synchronizes organization-published skills. It also wires a Claude Code session-start hook that runs quiet skill repair.
- On that hook, the package fetches organization skills using the wired token and writes returned skill bodies into the skill directories of detected agent CLIs, without per-update approval.
- The skill fetch uses the package's Agnoclast API endpoint. The inspected source does not establish malicious skill content or a separate attack.
- The other inspected integration paths detect or configure supported editors, remove package-managed entries on explicit uninstall, locate a transcript by session ID, or write an Antigravity watcher artifact that is not activated at load.
Evidence against
- The skill installation begins with an explicit setup or install command; the manifest does not trigger it during npm installation.
- The skill sync is an intended organization feature using the package's service endpoint. No malicious payload or credential theft was established.
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 Limitedbin/cortex-mcp.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@0.9.232.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.232 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.