registry / @theronap/agnoclast-mcp / 0.9.288
@theronap/agnoclast-mcp@0.9.288
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe package has no install lifecycle scripts, and the flagged configuration and closeout behaviors are reached through user-run CLI commands. The reviewed credential proof is sent to the configured Agnoclast service, consistent with the package's purpose.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
The MCP server runs when configured as an editor entry; configuration changes and background closeout require CLI commands.
Impact
No unauthorized credential transfer, hidden persistence, or unsolicited agent-control mutation was identified in the reviewed paths.
Mechanism
Requests use the configured Agnoclast service base, while channel and closeout features write configuration or persistence only when invoked.
AI rationale
The package has no install lifecycle scripts, and the flagged configuration and closeout behaviors are reached through user-run CLI commands. The reviewed credential proof is sent to the configured Agnoclast service, consistent with the package's purpose.
Evidence
~/.claude.json~/.claude/settings.json~/.codex/hooks.json~/.cursor/mcp.json~/.codex/config.toml~/Library/LaunchAgents/com.agnoclast.closeout.plist
Network endpoints2
agnoclast.com${base}/api/brains/confidential/agent-session
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest defines no install, preinstall, or postinstall hook.
- Background session closeout is exposed as an explicit CLI command and is documented as off by default.
- The channel configuration writer is reached through the explicit `channel` command.
- Confidential-session account proof is sent in an authenticated request to the configured Agnoclast service base.
Evidence against
- The package includes network access and writes to AI-agent configuration files, but the reviewed paths tie those behaviors to the package's integration features or explicit commands.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
16 flaggedlib/capture.mjsView file
•matchType = normalized_sha256
matchedPackage = @theronap/agnoclast-mcp@0.9.285
matchedPath = lib/capture.mjs
matchedIdentity = npm:QHRoZXJvbmFwL2Fnbm9jbGFzdC1tY3A:0.9.285
similarity = 1.000
summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity
Source file is highly similar to a previously finalized malicious package; 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
14 High3 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/channel.mjs
HighTrigger Reachable Persistencelib/closeout.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
HighKnown Malware Source Similaritylib/confidential_session.mjs
HighKnown Malware Source Similaritylib/login.mjs
HighKnown Malware Source Similaritylib/capture.mjs
HighKnown Malware Source Similaritylib/edge_extract.mjs
HighKnown Malware Source Similaritylib/graphify_sync.mjs
HighKnown Malware Source Similaritylib/obligations_worker.mjs
HighKnown Malware Source Similaritylib/confidential_guard.mjs
HighKnown Malware Source Similarity
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.288.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.288 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.