@theronap/cortex-mcp@0.9.186
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 25d ago · by lpm-firewall-aiThe source shows first-party agent configuration and skill setup, activated by an explicit CLI command. Under the agent integration policy this warrants a warning for the capability, but the inspected code does not establish malicious behavior or an automatic install-time attack.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The user runs the package's setup or install command; Antigravity activation additionally requires manual launchd loading.
Impact
These changes extend the package's behavior within configured agent environments; inspection did not establish an unconsented install-time attack or credential theft.
Mechanism
Setup writes agent configuration and hook files, installs managed skills, and can generate a launchd watcher and sync script.
AI rationale
The source shows first-party agent configuration and skill setup, activated by an explicit CLI command. Under the agent integration policy this warrants a warning for the capability, but the inspected code does not establish malicious behavior or an automatic install-time attack.
Evidence
bin/cortex-mcp.mjslib/setup.mjslib/skills.mjslib/editors/antigravity.mjspackage.json
Decision evidence
public snapshotAI called this Suspicious at 81.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The explicit setup command writes MCP and capture-hook configuration into supported agent CLIs and installs managed skills.
- Antigravity setup can write a launchd watcher and sync script; it does not load the watcher automatically and reports that manual activation is needed.
- The package manifest has no preinstall, install, or postinstall hook.
- Uninstall is a separately invoked command and supports a dry-run mode.
- The Codex, Cursor, skills, transcript-search, and capture target locations implement agent integration or session support; inspection found no concrete attack behavior in them.
Evidence against
- Setup requires an explicit command; no npm lifecycle hook triggers the agent configuration changes.
- The capture code sends session digests through the Cortex service client, with secret redaction and a local queue for failed delivery.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
Source & flagged code
6 flaggedlib/capture.mjsView file
•matchType = previous_version_dangerous_delta
matchedPackage = @theronap/cortex-mcp@0.9.150
matchedIdentity = npm:QHRoZXJvbmFwL2NvcnRleC1tY3A:0.9.150
similarity = 0.826
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'
...
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
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@0.9.186.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.186 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.