OpenCortex

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: opencortex Version: 3.6.7 OpenCortex is a comprehensive memory management framework for OpenClaw agents that implements structured knowledge storage, nightly distillation, and weekly synthesis. The bundle includes well-engineered security features, such as an AES-256 encrypted vault (vault.sh) that supports system keyrings (secret-tool/macOS Keychain) and a git backup utility (git-backup.sh) that uses an isolated-copy approach to scrub secrets before committing. While the system has broad access to workspace data and includes optional features like voice profiling and infrastructure collection, these are clearly documented as opt-in, operate entirely within the local workspace, and follow security best practices to prevent data leakage.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

OpenCortex can keep running scheduled memory-maintenance tasks without you manually invoking it each time.

Why it was flagged

The skill intentionally creates autonomous scheduled agent sessions. This is disclosed and matches the self-improving memory purpose, but it means the agent will continue performing maintenance after installation.

Skill content
Two cron jobs, both running as isolated OpenClaw agent sessions scoped to the workspace
Recommendation

Install only if you want persistent scheduled memory jobs, and keep the documented cron deletion/disable steps handy.

What this means

Personal details, preferences, contacts, and work context may be retained and reused by future agent sessions.

Why it was flagged

The daily maintenance instructions persist user, contact, preference, and communication information into files that can influence later sessions. This is core to the skill, but it increases the importance of reviewing stored memory.

Skill content
Distill ALL useful information into the right file ... Contacts mentioned → memory/contacts/ ... Preferences stated → memory/preferences.md ... User info and communication style → USER.md
Recommendation

Periodically review the memory files, especially USER.md, memory/preferences.md, memory/contacts/, and archived logs, and remove information you do not want retained.

NoteHigh Confidence
ASI08: Cascading Failures
What this means

A bad summary or reorganization could make future agent sessions rely on incorrect or misplaced memory.

Why it was flagged

Weekly synthesis can automatically restructure memory across multiple files. This is purpose-aligned, but mistakes in interpretation could propagate into future memory retrieval.

Skill content
Fix automatically — for issues within the agent's control: split oversized files into focused sub-files, move misplaced content to the correct file ... consolidate scattered duplicates, update MEMORY.md index
Recommendation

Review weekly summaries and important memory-file changes, especially after large or sensitive projects.

What this means

If you enable the vault, the skill may rely on a passphrase from an environment variable, system keyring, or optional local file.

Why it was flagged

The skill supports an encrypted vault and optional passphrase handling. This is expected for its secret-storage feature, but it involves sensitive credential material.

Skill content
OPENCORTEX_VAULT_PASS ... Vault passphrase via env var. Prefer system keyring ... .vault/.passphrase
Recommendation

Prefer the system keyring, avoid file-based passphrases unless necessary, and keep .vault/ and .secrets-map out of version control.

What this means

Using the --push option can upload memory/workspace history to your git remote, including non-secret personal or project context that scrubbing may not remove.

Why it was flagged

The backup helper can push a scrubbed commit to the configured git remote when explicitly run with --push. The feature is disclosed as off by default, but it can publish workspace contents if enabled.

Skill content
if [ "$PUSH" = "--push" ]; then
  git push --quiet 2>/dev/null
  echo "✅ Pushed to remote."
Recommendation

Use local backup by default; only enable --push for trusted private remotes after reviewing .gitignore and .secrets-map.

What this means

A user might overlook that git push is still a possible network operation if explicitly enabled.

Why it was flagged

This reassuring statement is mostly aimed at telemetry/phone-home behavior, but the same artifacts also document optional git push. The optional network path is disclosed, so this is an ambiguity rather than evidence of deception.

Skill content
OpenCortex contains zero network operations — no telemetry, no phone-home, no external endpoints.
Recommendation

Treat the no-network claim as applying to default setup/telemetry, and separately review any git backup or push configuration.