メニュー
Tamper-resistant audit watchdog for Clawdbot agents. Detects and logs suspicious filesystem activity with HMAC-chained evidence.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | clauditor |
| description | Tamper-resistant audit watchdog for Clawdbot agents. Detects and logs suspicious filesystem activity with HMAC-chained evidence. |
| homepage | https://github.com/apollostreetcompany/clauditor |
| metadata | {"clawdbot":{"emoji":"🛡️","requires":{"bins":["cargo","systemctl"],"os":"linux"}}} |
Security watchdog that monitors filesystem activity and creates tamper-evident logs. Even if Clawdbot is compromised, it cannot stop the watchdog, forge entries, or delete evidence.
Use the CLI wizard to guide users through installation:
cd /path/to/clauditor
cargo build --release
Check status: ./target/release/clauditor wizard status
current_step (1-6) and complete (true/false)Get next step: ./target/release/clauditor wizard next
User runs the sudo command
Verify: ./target/release/clauditor wizard verify
Repeat until complete: true
User: "Install clauditor"
Agent: [runs wizard status → current_step: 1]
Agent: "Step 1 of 6: Create system user
This creates a 'sysaudit' user that runs the watchdog. Even if you're
compromised, you can't kill a process owned by another user.
Run this:
sudo useradd --system --shell /usr/sbin/nologin --no-create-home sysaudit
Let me know when done."
User: "done"
Agent: [runs wizard verify → success]
Agent: [runs wizard next → step 2...]
systemctl status systemd-journaldd
./target/release/clauditor digest \
--log /var/lib/.sysd/.audit/events.log \
--key /etc/sysaudit/key \
--format markdown
sudo bash wizard/wizard.sh
/etc/sysaudit/config.toml/etc/sysaudit/key/var/lib/.sysd/.audit/events.logEdit config to customize watch_paths and target_uid.
The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.
Advanced OpenClaw skill creation handler that executes the official 5-step research flow with comprehensive analysis and best practices. Ensures proper methodology when users request to create or modify OpenClaw/Moltbot/ClawDBot skills following official standards.
Create curated digests of agent conversations (e.g., Moltbook) by collecting posts, clustering themes, ranking signal, and producing a concise digest with takeaways, collaborators, and next actions. Use when asked to summarize agent forums, build a daily/weekly digest, identify who to follow, or extract opportunities from noisy feeds.
Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated artifacts, structured claims, milestone tracking, and independent replications. Claim replication bounties, submit peer reviews, and collaborate with other AI researchers.
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
Unblock websites and bypass CAPTCHAs and 403 errors using Aluvia mobile proxies. Enables web search and content extraction without browser automation.