Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gensecaihq/Wazuh-Autopilot --skill threat-actor-attributiongit clone --depth 1 https://github.com/gensecaihq/Wazuh-AutopilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/threat-actor-attribution)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/threat-actor-attribution"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/threat-actor-attribution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/threat-actor-attribution"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/threat-actor-attribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00760 |
| Opus 5.5 | $0.00020 | $0.00304 |
| Sonnet 5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
threat-actor-attribution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Threat Actor Attribution
Attribution is rarely needed to respond, and wrong attribution causes real harm (misdirected response, bad executive decisions). Do it carefully or not at all.
When to attempt
Attempt only if at least two of these hold:
- Infrastructure (IP/domain) with a reliable (A/B) public link to a named cluster.
- Tooling or malware family with known actor associations.
- A distinctive TTP sequence matching an ATT&CK group profile.
- Targeting consistent with the actor's known sector/geography interest.
Otherwise record "attribution not assessed — insufficient evidence" and stop.
Diamond Model
Describe the intrusion on four vertices and the links between them:
| Vertex | Questions | Evidence sources |
|---|---|---|
| Adversary | Who operates it? (often unknown — that's fine) | intel reporting |
| Capability | Tools, malware, exploits, techniques | host forensics, ATT&CK mapping |
| Infrastructure | IPs, domains, C2, hosting | IOC enrichment |
| Victim | Which assets, users, sector | case entities, org context |
Meta-features: timestamp, phase (ATT&CK tactic), result, direction, methodology. Pivot vertex-to-vertex (e.g. infrastructure → other victims seen in intel) to test links.
Comparing to ATT&CK groups
- List the case's confirmed techniques (from
mitre-attack-mapping). - Compare with candidate groups' technique sets from public ATT&CK group pages
(via
search_external_contextfor the group name — public data only). - Overlap on common techniques (T1059, T1078, T1110) means little; weight distinctive techniques and tool names higher.
- Record competing hypotheses, including "unknown / commodity actor".
Estimative language (ICD 203 style)
Use consistent probability terms and state confidence separately:
| Term | Approx. probability |
|---|---|
| almost no chance / remote | 1–5% |
| very unlikely | 5–20% |
| unlikely | 20–45% |
| roughly even chance | 45–55% |
| likely | 55–80% |
| very likely | 80–95% |
| almost certainly | 95–99% |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 79 lines · 50 tokens per session scan A 758375c00482
threat-actor-attribution is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 760 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
agent-performance-monitor
Agent skill for performance-monitor - invoke with $agent-performance-monitor.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.