registry / @theronap/agnoclast-mcp / 0.9.286
@theronap/agnoclast-mcp@0.9.286
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe inspected credential flow sends account proof to the configured Agnoclast API for a requested confidential-brain session. Configuration migration is scoped to an existing package entry, and the persistence hint requires explicit wiring and activation; the source does not show an attack.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
A user runs the MCP server, requests a confidential brain, or explicitly wires the Antigravity adapter.
Impact
No malicious credential transfer, unrelated persistence, or unauthorized account action was identified.
Mechanism
The confidential-session request sends proof to the configured Agnoclast API. The server-start migration only updates an existing old package entry and its matching tool permissions; Antigravity wiring writes artifacts but does not activate launchd.
AI rationale
The inspected credential flow sends account proof to the configured Agnoclast API for a requested confidential-brain session. Configuration migration is scoped to an existing package entry, and the persistence hint requires explicit wiring and activation; the source does not show an attack.
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package declares no install, preinstall, or postinstall lifecycle scripts; its executable is bin/cortex-mcp.mjs.
- The confidential-session code sends account proof to the configured Agnoclast API endpoint as part of a request to open a named confidential brain.
- The automatic key migration is limited to configurations that still have the package’s old `cortex` entry and migrates it to `agnoclast`.
- The Antigravity adapter writes its sync script and launchd plist only when its `wire()` function runs, and says it does not load the agent automatically.
Evidence against
- Starting the MCP server can run a migration that updates Claude configuration and adds allow rules for the renamed tool namespace.
- Antigravity’s generated watcher can run a sync script after a user activates its launchd agent.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStrings
Source & flagged code
16 flaggedlib/capture.mjsView file
•matchType = normalized_sha256
matchedPackage = @theronap/agnoclast-mcp@0.9.285
matchedPath = lib/capture.mjs
matchedIdentity = npm:QHRoZXJvbmFwL2Fnbm9jbGFzdC1tY3A:0.9.285
similarity = 1.000
summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity
Source file is highly similar to a previously finalized malicious package; 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
14 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
HighKnown Malware Source Similaritylib/confidential_session.mjs
HighKnown Malware Source Similaritylib/login.mjs
HighKnown Malware Source Similaritylib/capture.mjs
HighKnown Malware Source Similaritylib/edge_extract.mjs
HighKnown Malware Source Similaritylib/graphify_sync.mjs
HighKnown Malware Source Similaritylib/obligations_worker.mjs
HighKnown Malware Source Similaritylib/confidential_guard.mjs
High
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.286.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.286 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.