registry / @theronap/agnoclast-mcp / 0.9.283
@theronap/agnoclast-mcp@0.9.283
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe flagged credential flow requests access to a confidential brain through the configured Cortex API when that brain is explicitly named in a tool call. Setup and editor configuration changes are command-driven, and the Antigravity adapter does not activate its generated launch agent.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Explicit setup/install commands wire editor configuration; a confidential session opens when a tool call names a confidential brain.
Impact
No malicious impact identified in the inspected flows.
Mechanism
The session proves the signed-in AI account and sends that proof with the user’s Cortex token to the configured Cortex API to request a seat token. Antigravity artifacts are written but not activated by the adapter.
AI rationale
The flagged credential flow requests access to a confidential brain through the configured Cortex API when that brain is explicitly named in a tool call. Setup and editor configuration changes are command-driven, and the Antigravity adapter does not activate its generated launch agent.
Evidence
~/.claude.json~/.claude/settings.json~/.cortex/antigravity-sync.sh~/Library/LaunchAgents/com.cortex.antigravity-sync.plist
Decision evidence
public snapshotAI called this Clean at 88.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest describes an MCP integration for the publisher’s Cortex service.
- Configuration setup and cross-editor installation are explicit CLI commands.
- Confidential-session proof is sent with a seat-token request to the configured Cortex API after a tool names a confidential brain.
- The Antigravity adapter writes a launch agent file but does not activate it; it tells the user to load it.
- The status command’s automatic guard repair is described as applying the guard for the next session.
Evidence against
- The package reads Codex and Claude account proof, so credential handling warrants scrutiny; the inspected flow sends proof to the configured Cortex API as part of an explicitly requested confidential-brain action.
- No install lifecycle scripts are declared.
- The persistence hint is bounded: the adapter writes artifacts but does not load the launch agent.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
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/editors/claude.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
4 High3 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/channel.mjs
HighTrigger Reachable Persistencelib/editors/antigravity.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
HighPrevious Version Dangerous Deltalib/confidential_session.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/agnoclast-mcp@0.9.283.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.283 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.