registry / @theronap/agnoclast-mcp / 0.9.237
@theronap/agnoclast-mcp@0.9.237
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe package has a real first-party agent extension lifecycle: setup enables later automatic skill refreshes in agent skill directories. This supports a warning, while the inspected behavior does not establish a concrete attack.
Static reason
No blocking static signals were detected.
Trigger
A user runs setup, then Claude starts a session and runs the configured skill repair hook.
Impact
Agent instructions may be added or refreshed automatically after setup, creating a first-party agent extension lifecycle risk; this source behavior does not establish malicious control hijacking.
Mechanism
The hook fetches skills from the configured Cortex API with the wired token and writes them into detected Claude and Codex skill folders.
AI rationale
The package has a real first-party agent extension lifecycle: setup enables later automatic skill refreshes in agent skill directories. This supports a warning, while the inspected behavior does not establish a concrete attack.
Evidence
lib/editors/claude.mjslib/skills.mjslib/setup.mjs~/.claude/settings.json~/.claude/skills~/.codex/skills~/.cortex/org-skills-cache.json
Network endpoints1
CORTEX_URL/api/skills
Decision evidence
public snapshotAI called this Suspicious at 87.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- package.json defines no install, preinstall, or postinstall lifecycle hook.
- The CLI adds setup wiring only when the user invokes the setup command; the installer requires a token or an existing wired token.
- Setup adds a Claude session-start hook that runs the skill repair command.
- The skill updater fetches organization-published skills from the configured Cortex API using the wired token, then installs them into detected Claude and Codex skill directories.
- Antigravity’s generated watcher requires a separate launchctl command to activate.
Evidence against
- The inspected sources show package-aligned agent extension behavior, with no evidence of credential theft or malicious payload execution.
- The flagged uninstall code removes managed agent configuration when the user invokes uninstall.
- Antigravity’s watcher is not activated automatically by the package.
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/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/agnoclast-mcp@0.9.237.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-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.