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 meltedinhex/analyst-ai-pack --skill enriching-iocs-with-threat-intel-sourcesgit clone --depth 1 https://github.com/meltedinhex/analyst-ai-packWrote 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/meltedinhex/analyst-ai-pack/enriching-iocs-with-threat-intel-sources)<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/enriching-iocs-with-threat-intel-sources"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/enriching-iocs-with-threat-intel-sources/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/meltedinhex/analyst-ai-pack/enriching-iocs-with-threat-intel-sources"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/enriching-iocs-with-threat-intel-sources.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 | $0.00075 | $0.00741 |
| Opus 5 | $0.00037 | $0.00370 |
| Sonnet 5 | $0.00015 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
enriching-iocs-with-threat-intel-sources 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 12d ago.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enriching IOCs with Threat Intel Sources
When to Use
- You have atomic indicators and need context: reputation, related infrastructure, first/last seen, and known associations.
- You are scoring indicator confidence before acting or reporting.
- You must plan lookups without leaking your investigation to the adversary.
Do not use active interaction (visiting a C2 URL, resolving a live domain from your own network) for enrichment — use passive sources to avoid tipping off the adversary.
Prerequisites
- Defanged indicators (from the defanging skill) and access to enrichment sources/APIs.
- Awareness of each source's operational-security implications.
Safety & Handling
- Prefer passive sources (passive DNS, sample DBs, reputation feeds) over active probing.
- Never submit a customer/internal sample to a public sandbox without authorization — it becomes publicly retrievable and can expose sensitive data.
Workflow
Step 1: Group indicators by type
Separate hashes, domains, IPs, and URLs; each maps to different enrichment sources.
Step 2: Plan the right lookups
Map each type to passive sources: hashes → sample/AV databases; domains → passive DNS, WHOIS, reputation; IPs → ASN/geo, passive DNS, reputation; URLs → URL reputation/sandbox history.
python scripts/analyst.py plan iocs.json
Step 3: Score confidence
Combine source agreement, age, and prevalence into a confidence score; a single hit on one feed is weaker than corroboration across independent sources.
Step 4: Annotate and pivot
Attach context (first seen, related infrastructure, family) and pivot on strong links (shared registrant, hosting, certificate) to expand the picture.
Step 5: Record provenance
Note which source provided each piece of context and when, so the enrichment is auditable and re-checkable.
Validation
- Each indicator is routed to type-appropriate, passive sources.
- Confidence reflects corroboration across independent sources, not a single feed.
- Every enrichment carries source and timestamp provenance.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 98 lines · 75 tokens per session scan A 327a3c2b9c09
enriching-iocs-with-threat-intel-sources is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 741 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…
building-ioc-enrichment-pipeline-with-opencti
OpenCTI is an open-source platform for managing cyber threat intelligence knowledge, built on STIX 2.1 as its native data model. This skill covers building an automated IOC enrichment pipeline using O.
analyzing-malicious-pdf-with-peepdf
A Chinese-language skill for examining suspicious PDF files with peepdf, pdfid, and pdf-parser. It is intended for static malware analysis, which studies a file without running it.
intelthreadlinqs-mcp-skill
Operate the Threadlinqs Intelligence MCP server — 73 threat-intelligence tools covering threats, detection rules in Splunk SPL / Microsoft KQL / Sigma, IOCs, threat actors, CVE/CWE enrichment, MITRE ATT&CK coverage and prediction, C2 infrastructure, the correlation graph, and STIX 2.1 / ATT&CK Navigator export. Use…
analyzing-malicious-pdf-with-peepdf
Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects.