registry / @theronap/cortex-mcp / 0.9.238
@theronap/cortex-mcp@0.9.238
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 18d ago · by lpm-firewall-aiNo install lifecycle hook triggers the flagged configuration writes, and setup is explicitly invoked. However, setup enables later automatic synchronization of organization-published agent instructions, leaving a concrete guarded extension risk; the inspected source does not establish malicious behavior.
Static reason
No blocking static signals were detected.
Trigger
A user runs setup; subsequent configured skill-repair hooks can synchronize organization-published skills.
Impact
Published skill content can affect later agent behavior; misuse of organization publishing access could change those instructions without another local setup action.
Mechanism
The package fetches the organization's published skills using the wired token and writes their content into detected agent skill directories.
AI rationale
No install lifecycle hook triggers the flagged configuration writes, and setup is explicitly invoked. However, setup enables later automatic synchronization of organization-published agent instructions, leaving a concrete guarded extension risk; the inspected source does not establish malicious behavior.
Evidence
lib/skills.mjslib/setup.mjs
Decision evidence
public snapshotAI called this Suspicious at 84.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- package.json defines a CLI entrypoint and contains no preinstall, install, or postinstall hook.
- The Codex and Cursor adapters write their configuration when their wire functions are called.
- Setup requires a token argument and is dispatched as an explicit CLI command.
- Bundled skills are installed into detected agent skill directories; setup also pulls organization-published skills.
- Organization skills are fetched with the wired token and installed into detected agent skill directories; setup invokes this sync.
- The setup flow can automatically install or update organization-published agent instructions, leaving residual risk if trusted organization publishing access is misused.
Evidence against
- Uninstall runs only through an explicit command and supports a dry run; it backs up files before edits.
- The Antigravity adapter writes artifacts but does not activate its watcher; its generated plist sets RunAtLoad to false.
- Working-file tracking is described as attention data and does not grant access.
- The CLI dispatches setup and install as separate commands; no package lifecycle hook triggers these writes.
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@0.9.238.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.238 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.