registry / @theronap/agnoclast-mcp / 0.9.279
@theronap/agnoclast-mcp@0.9.279
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 supports confidential-brain access through Agnoclast's own API, and the flagged Antigravity persistence is written without automatic activation. The manifest declares no install lifecycle hooks, and the reviewed source shows no malicious behavior.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The MCP server checks confidential-brain access at startup; a tool call naming a confidential brain requests a seat token. The Antigravity adapter writes its artifacts when invoked by install.
Impact
No unauthorized collection, foreign credential transfer, or active persistence was identified.
Mechanism
Requests use the Agnoclast service API. The Antigravity launch agent is not set to run at load and requires manual activation.
AI rationale
The flagged credential flow supports confidential-brain access through Agnoclast's own API, and the flagged Antigravity persistence is written without automatic activation. The manifest declares no install lifecycle hooks, and the reviewed source shows no malicious behavior.
Evidence
~/.cortex/confidential-sessions/<sha256(sessionKey)>~/.cortex/antigravity-sync.sh~/Library/LaunchAgents/com.cortex.antigravity-sync.plist
Network endpoints1
agnoclast.com
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no install, preinstall, or postinstall hook; its npm scripts are release, promote, and rollback.
- Confidential session credentials are sent to the Agnoclast API when a tool call names a confidential brain; the source identifies agnoclast.com as the canonical service host.
- The Antigravity launch agent is written with RunAtLoad disabled, and the adapter tells the user to load it manually.
Evidence against
- The server reads AI account proof and sends it with the user's Agnoclast token for confidential-brain access.
- The package can write an Antigravity script and launch-agent plist when its install adapter is run.
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
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@0.9.279.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.279 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.