agent-audit-trail
暂无简介
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
03 SKILL.md 正文
Agent Audit Trail Skill
Tamper-evident, hash-chained audit logging for AI agents. EU AI Act compliant.
Why
AI agents act on your behalf. From 2 August 2026, the EU AI Act requires automatic logging, tamper-evident records, and human oversight capability for AI systems. This skill provides all three with zero dependencies.
Quick Start
1. Add to your agent's workspace
cp scripts/auditlog.py /path/to/your/workspace/scripts/
chmod +x /path/to/your/workspace/scripts/auditlog.py
2. Log an action
./scripts/auditlog.py append \
--kind "file-write" \
--summary "Created config.yaml" \
--target "config.yaml" \
--domain "personal"
3. Verify integrity
./scripts/auditlog.py verify
# Output: OK (N entries verified)
Compliance Mapping
| EU AI Act Article | Requirement | How This Skill Helps |
|---|---|---|
| Art. 12 Record-Keeping | Automatic event logging | Every action logged with timestamp, actor, domain, target |
| Art. 12 Integrity | Tamper-evident records | SHA-256 hash chaining — modification breaks the chain |
| Art. 14 Human Oversight | Human approval linkage | --gate flag links actions to human approval references |
| Art. 50 Transparency | Auditable records | Human-readable NDJSON, one-command verification |
| Art. 12 Traceability | Chronological ordering | Monotonic ord tokens |
Event Kinds
Use these standardised event types for consistent audit trails:
| Kind | When to Use |
|---|---|
file-write |
Agent creates or modifies files |
exec |
Agent runs a command |
api-call |
External API interaction |
decision |
AI makes or recommends a decision |
credential-access |
Secrets or credentials accessed |
external-write |
Agent writes to external systems |
human-override |
Human overrides an AI decision |
disclosure |
AI identity disclosed to user |
Full Documentation
See README.md for complete usage, integration examples, security model, and EU AI Act compliance guide.
Log Format
{
"ts": "2026-02-24T07:15:00+00:00",
"kind": "exec",
"actor": "atlas",
"domain": "ops",
"plane": "action",
"target": "pg_dump production",
"summary": "Ran database backup",
"gate": "approval-123",
"ord": 42,
"chain": {"prev": "abc...", "hash": "def...", "algo": "sha256(prev\\nline_c14n)"}
}
OpenClaw Integration
Add to HEARTBEAT.md:
## Audit integrity check
- Run: `./scripts/auditlog.py verify`
- If fails: alert with line number + hash mismatch
- If OK: silent
Requirements
- Python 3.9+ (zero external dependencies)
- MIT License
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.