@theronap/cortex-mcp@0.9.137
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package has a real, user-invoked agent-control and session-ingestion capability with remotely refreshed instructions. It lacks an npm lifecycle trigger or concrete evidence of malicious execution, so warning is more proportionate than blocking.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The user runs setup or install, then starts or ends an enabled agent session.
Impact
Future agent sessions can execute package commands, receive remotely supplied skills, and send captured session material to the configured service.
Mechanism
Agent configuration mutation, automatic hooks, remote skill synchronization, and session ingestion.
AI rationale
The package has a real, user-invoked agent-control and session-ingestion capability with remotely refreshed instructions. It lacks an npm lifecycle trigger or concrete evidence of malicious execution, so warning is more proportionate than blocking.
Evidence
lib/setup.mjslib/editors/claude.mjslib/capture.mjslib/skills.mjslib/editors/antigravity.mjs~/.claude.json~/.claude/settings.json~/.codex/config.toml~/.codex/hooks.json~/.claude/skills/<name>/SKILL.md~/.codex/skills/<name>/SKILL.md~/.cortex/antigravity-sync.sh~/Library/LaunchAgents/com.cortex.antigravity-sync.plist
Network endpoints2
agnoclast.com/api/ingestagnoclast.com/api/skills
Decision evidence
public snapshotAI called this Suspicious at 90.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The explicit setup command adds automatic Claude hooks, including a session-start command that refreshes skills.
- The capture hook reads session data and posts an ingestion body with its bearer token to Agnoclast.
- Server-provided skills are installed into detected Claude and Codex skill directories during automatic repair.
- The Antigravity adapter writes a launchd plist and shell script, although it does not load the agent itself.
Evidence against
- package.json has no preinstall, install, or postinstall script.
- The configuration and hook changes require an explicit setup or install command.
- Network requests use the package-aligned agnoclast.com service and an explicit token.
- No obfuscation, evaluator use, credential harvesting beyond the configured token, or self-dependency was found.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
Source & flagged code
6 flaggedlib/capture.mjsView file
•matchType = previous_version_dangerous_delta
matchedPackage = @theronap/cortex-mcp@0.9.135
matchedIdentity = npm:QHRoZXJvbmFwL2NvcnRleC1tY3A:0.9.135
similarity = 0.872
summary = stored previous version shares package body but lacks this dangerous source file
High
Previous Version Dangerous Delta
This package version adds a dangerous source file absent from the previous stored version; 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'
...
L17: if (!res.ok) return null
L18: const j = await res.json().catch(() => ({}))
L19: return Array.isArray(j.types) ? j.types : null
...
L31: try {
L32: if (resolve(String(cwd)) === homedir()) return 'general'
L33: } catch { /* unresolvable path — fall through to basename */ }
...
L41: //
L42: // Handles the four remote forms git emits: scp-like ssh (git@github.com:o/n.git), ssh://, https://,
L43: // 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
4 High3 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
HighPrevious Version Dangerous Deltalib/capture.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/cortex-mcp@0.9.137.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.137 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.