@theronap/agnoclast-mcp@0.9.185
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-aiStatic source inspection found conditional credential exposure: skills sync forwards a wired token to a configurable destination without enforcing a service allowlist. The behavior supports a warning, but does not establish default exfiltration or malicious intent.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
Run setup or a skills sync while CORTEX_URL is set to an untrusted destination.
Impact
A configured destination could receive the existing service token and use it outside its intended service.
Mechanism
The sync resolves a token from the environment or existing agent configuration, then sends it in an Authorization bearer header. The URL resolver permits arbitrary destinations beyond a narrow protected-host check.
AI rationale
Static source inspection found conditional credential exposure: skills sync forwards a wired token to a configurable destination without enforcing a service allowlist. The behavior supports a warning, but does not establish default exfiltration or malicious intent.
Evidence
lib/skills.mjslib/diagnose.mjslib/setup.mjsbin/cortex-mcp.mjs
Decision evidence
public snapshotAI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The manifest defines a CLI and release scripts, with no npm install lifecycle hook; setup is a CLI command.
- The skills sync reads an existing wired token and sends it as a bearer token to the skills endpoint.
- CORTEX_URL can select an arbitrary destination; the resolver rejects certain protected deployment URLs but does not enforce a service allowlist.
- Setup invokes skills sync, which installs returned organization skills into detected agent CLI skill directories.
- The inspected editor, uninstall, skills, and working-file locations show agent configuration, managed cleanup, skill handling, and session transcript tracking.
Evidence against
- The token send occurs in the organization skills sync flow; no source inspected here establishes a hidden default recipient or theft intent.
- The Antigravity adapter writes artifacts but does not activate its watcher itself.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
Source & flagged code
6 flaggedlib/capture.mjsView file
•matchType = previous_version_dangerous_delta
matchedPackage = @theronap/agnoclast-mcp@0.9.150
matchedIdentity = npm:QHRoZXJvbmFwL2Fnbm9jbGFzdC1tY3A:0.9.150
similarity = 0.848
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/agnoclast-mcp@0.9.185.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.185 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.