registry / @theronap/cortex-mcp / 0.9.237
@theronap/cortex-mcp@0.9.237
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-aiWarn because explicit setup enables automatic updates to agent skill instructions from organization-published content. The package has no install lifecycle hook, and the inspected integration source does not establish malicious execution.
Static reason
No blocking static signals were detected.
Trigger
A user runs setup or repair, then starts a Claude session with the installed SessionStart hook enabled.
Impact
Organization-published skill changes can update instructions available to an agent without a separate prompt for each update.
Mechanism
The hook fetches authenticated organization skill content and installs it into the Claude and Codex skill directories; later Claude sessions repeat the refresh.
AI rationale
Warn because explicit setup enables automatic updates to agent skill instructions from organization-published content. The package has no install lifecycle hook, and the inspected integration source does not establish malicious execution.
Evidence
bin/cortex-mcp.mjslib/setup.mjslib/editors/claude.mjslib/skills.mjs~/.claude/settings.json~/.claude/skills/<name>/SKILL.md~/.codex/skills/<name>/SKILL.md
Decision evidence
public snapshotAI called this Suspicious at 88.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- package.json has no preinstall, install, or postinstall hook.
- The CLI invokes setup through an explicit subcommand; setup installs managed skills and wires later repair behavior.
- The Claude SessionStart hook runs skill repair, which fetches authenticated organization skill content and writes it into agent skill directories.
- Codex lacks a SessionStart hook in this adapter, and Cursor is capture-only.
- Antigravity setup writes a launchd plist but does not activate it; activation requires a separate load command.
Evidence against
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
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@0.9.237.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.237 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.