registry / @theronap/agnoclast-mcp / 0.9.226
@theronap/agnoclast-mcp@0.9.226
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 25d ago · by lpm-firewall-aiSource inspection found no npm install lifecycle hook or concrete malicious behavior. Agent configuration and skills are managed through explicit CLI flows, while the flagged Antigravity artifact setup does not load its launch agent.
Static reason
No blocking static signals were detected.
Trigger
A user invokes the package's setup, install, skills, or uninstall command.
Impact
These actions configure or remove the package's assistant integration. No unconsented attack behavior was established.
Mechanism
The CLI writes package integration settings and skills to assistant-specific locations; Antigravity artifacts are written without loading the launch agent.
AI rationale
Source inspection found no npm install lifecycle hook or concrete malicious behavior. Agent configuration and skills are managed through explicit CLI flows, while the flagged Antigravity artifact setup does not load its launch agent.
Evidence
package.jsonlib/editors/codex.mjslib/editors/cursor.mjslib/setup.mjslib/skills.mjslib/uninstall.mjslib/working_files.mjslib/editors/antigravity.mjsbin/cortex-mcp.mjs
Decision evidence
public snapshotAI called this Clean at 79.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json contains release, promote, and rollback scripts, with no preinstall, install, or postinstall hook.
- Codex and Cursor adapter locations describe integration capabilities; their configuration wiring is reached through explicit setup/install commands.
- Setup writes assistant configuration after its CLI command is invoked; install resolves a supplied or already-wired token before wiring detected editors.
- Bundled skills are installed into Claude Code and Codex skill directories by explicit skill setup flows.
- Uninstall targets package integration paths and has a dry-run option.
- Antigravity wiring writes artifacts without loading the launch agent; the inspected working-files path searches for the current session transcript.
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 High3 Medium6 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
LowScripts Present
LowWeak Cryptolib/capture.mjs
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowSuspicious Lifecycle Evidencepackage.json
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.226.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.226 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.