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 hypnguyen1209/offensive-claude --skill malware-analysisgit clone --depth 1 https://github.com/hypnguyen1209/offensive-claudeWrote 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/hypnguyen1209/offensive-claude/malware-analysis)<a href="https://agentmods.dev/skills/hypnguyen1209/offensive-claude/malware-analysis"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/malware-analysis/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/hypnguyen1209/offensive-claude/malware-analysis"><img src="https://agentmods.dev/badge/skills/hypnguyen1209/offensive-claude/malware-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to critical
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- critical YARA Match · line 7 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Rogue Agent · line 116 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00065 | $0.02686 |
| Opus 5 | $0.00032 | $0.01343 |
| Sonnet 5 | $0.00013 | $0.00537 |
| Haiku 4.5 | $0.00006 | $0.00269 |
Grade A, and why
malware-analysis 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 9d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Malware Analysis
When to Activate
- Triaging an unknown binary/script: identity, packing verdict, capability map, IOCs, go/no-go for detonation.
- Recovering the real payload from a packed/crypted/obfuscated loader (commodity loaders, RAT chains, .NET).
- Detonating safely and recovering fileless / in-memory artifacts (injection, AMSI/ETW patching, WMI persistence).
- Extracting malware configuration (C2, keys, sleep/jitter, campaign IDs) for threat intel and detection.
- Detecting/characterizing C2 on the wire (beacon cadence, JA4+ fingerprints, tunneled/DoH channels).
- Writing durable, low-FP YARA-X detection from analysis findings; incident-response scoping.
Technique Map
| Technique | ATT&CK | CWE | Reference | Script |
|---|---|---|---|---|
| Hash/imphash/Rich/ssdeep/TLSH triage + PE anomalies | T1027 | CWE-506 | references/static-triage-capa.md | scripts/triage.py |
| Per-section entropy + packer/RWX/EP heuristics | T1027.002 | CWE-1066 | references/static-triage-capa.md | scripts/triage.py |
| Obfuscated string recovery (FLOSS) | T1140, T1027.013 | CWE-656 | references/static-triage-capa.md | scripts/triage.py |
| Capability detection → ATT&CK (capa, static+dynamic) | T1027 | CWE-506 | references/static-triage-capa.md | scripts/triage.py |
| Emulation unpacking (Unicorn/unipacker/Speakeasy/Qiling) | T1140, T1620 | CWE-656 | references/unpacking-deobfuscation.md | scripts/auto_unpack.py |
| DBI unpacking via API hooks (Frida) | T1055, T1620 | CWE-656 | references/unpacking-deobfuscation.md | scripts/frida_unpack.js |
| .NET deobfuscation/unpacking (de4dot/dnSpyEx) | T1027, T1140 | CWE-656 | references/unpacking-deobfuscation.md | scripts/frida_unpack.js |
| Sandbox detonation + behavioral capture | T1497 | CWE-506 | references/dynamic-fileless-memory.md | scripts/mem_triage.py |
| Memory injection/hollowing/ghosting analysis (Vol3) | T1055, T1055.012 | CWE-506 | references/dynamic-fileless-memory.md | scripts/mem_triage.py |
| AMSI/ETW in-memory patch + patchless detection | T1562.001 | CWE-693 | references/dynamic-fileless-memory.md | scripts/mem_triage.py |
| Fileless WMI/registry/PowerShell persistence | T1546.003, T1547.001, T1059.001 | CWE-506 | references/dynamic-fileless-memory.md | scripts/mem_triage.py |
| Cobalt Strike / AdaptixC2 config extraction | T1071.001, T1573 | CWE-798 | references/config-c2-extraction.md | scripts/cs_config_extract.py |
| Config framework at scale (MACO/CAPE) | T1071.001 | CWE-798 | references/config-c2-extraction.md | scripts/cs_config_extract.py |
| Generic unknown-C2 protocol RE + decoder | T1573, T1071.004 | CWE-311 | references/config-c2-extraction.md | scripts/cs_config_extract.py |
| Beacon cadence/jitter detection (PCAP/Zeek) | T1071.001, T1029 | CWE-778 | references/network-c2-detection.md | scripts/beacon_profiler.py |
| JA4+ TLS/HTTP/cert fingerprinting (Sliver/Havoc JA4X) | T1071.001, T1573 | CWE-295 | references/network-c2-detection.md | scripts/beacon_profiler.py |
| Tunneled/DoH C2 surfacing (cloudflared/chisel) | T1572, T1568.002, T1071.004 | CWE-441 | references/network-c2-detection.md | scripts/beacon_profiler.py |
| YARA-X family rule authoring + FP validation | T1027 | CWE-506 | references/yara-detection-engineering.md | scripts/yara_gen.py |
What ships with it
13 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.
- references/config-c2-extraction.md 7.6 KB
- references/dynamic-fileless-memory.md 7.9 KB
- references/network-c2-detection.md 6.8 KB
- references/static-triage-capa.md 7.2 KB
- references/unpacking-deobfuscation.md 7.8 KB
- references/yara-detection-engineering.md 6.5 KB
- scripts/auto_unpack.py 6.8 KB runs code
- scripts/beacon_profiler.py 4.6 KB runs code
- scripts/cs_config_extract.py 5.0 KB runs code
- scripts/frida_unpack.js 4.5 KB runs code
- scripts/mem_triage.py 6.0 KB runs code
- scripts/triage.py 9.0 KB runs code
- scripts/yara_gen.py 5.9 KB runs code
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.
- 9d ago First seen · 121 lines · 65 tokens per session scan A 5106ffb534cf
malware-analysis is a skill published in the GitHub repository hypnguyen1209/offensive-claude (357 stars, last pushed 22d ago), licensed MIT. It adds 65 tokens to every session and 2,686 once invoked, about $0.0003 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
bt6-queue-audit
Audit the full pull-request and issue queue of a BT6 research or support repository, classifying readiness, evidence risk, and next action without mutating tracker state.
bt6-issue-steward
Triage and steward issues in BT6 research and support repositories, deciding whether to answer, reproduce, correct evidence, link work, design a feature, route security, implement, or close.
bt6-merge-train
Run an explicitly authorized, conservative BT6 merge train that processes validated pull requests one at a time and reconciles repository, CI, evidence, and issue state after each merge.
bt6-pr-audit
Audit one pull request in a BT6 research or support repository at an exact head SHA, covering correctness, research integrity, security, tests, contracts, and merge readiness.
bt6-provider-review
Audit an external AI/API provider and its integration into a BT6 repository for service reality, independent verification, trust boundaries, secret handling, API/model correctness, completeness, claim traceability, and merge readiness.
xiaohongshu-search-full
Search Xiaohongshu (XHS / RedNote) notes by keyword with full field extraction including body text, topics/tags, image list URLs, video stream URL, publish timestamp, and all engagement stats (likes, collects, comments, shares). Supports all page filter options: sort order (general, latest, most liked, most commented…