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 performing-dynamic-analysis-in-a-sandboxgit 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/performing-dynamic-analysis-in-a-sandbox)<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/performing-dynamic-analysis-in-a-sandbox"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/performing-dynamic-analysis-in-a-sandbox/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/performing-dynamic-analysis-in-a-sandbox"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/performing-dynamic-analysis-in-a-sandbox.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 | $0.00068 | $0.00811 |
| Opus 5 | $0.00034 | $0.00405 |
| Sonnet 5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
performing-dynamic-analysis-in-a-sandbox 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 8d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performing Dynamic Analysis in a Sandbox
When to Use
- Static analysis is blocked by packing/obfuscation and you need to observe runtime behavior.
- You want a behavioral picture: spawned processes, dropped files, registry edits, and C2.
- You are confirming capabilities hypothesized from static analysis.
Do not use dynamic analysis as the only method — evasive samples may sleep, detect the sandbox, or require arguments. Pair it with static/RE work.
Prerequisites
- An isolated lab with a victim VM and simulated internet (see the lab-setup skill).
- A sandbox stack (CAPE/Cuckoo) or manual instrumentation: Process Monitor, Process Explorer, Regshot, and a packet capture on the services guest.
- A clean base snapshot to revert to.
Safety & Handling
- Detonate only inside the isolated victim VM; revert the snapshot after each run.
- Route all network through the simulated-internet guest; never allow live egress.
- Defang any captured URLs/IPs before they leave the lab.
Workflow
Step 1: Prepare instrumentation
Start Process Monitor (filtered to the target), Regshot baseline, and packet capture on the services guest. Snapshot the victim as clean.
Step 2: Detonate with the right context
Many samples need a parent (Office, rundll32), an export (rundll32 dll,Export), or arguments.
Match the original delivery context or the sample stalls.
Step 3: Observe for the full behavior window
Watch process creation, file drops, registry Run keys/services, scheduled tasks, and network beacons. Give it several minutes; some samples sleep first.
Step 4: Summarize the report
Feed the sandbox JSON (or your collected logs) to the summarizer to group events into capabilities and IOCs:
python scripts/analyst.py summarize report.json
Step 5: Diff the system state
Compare Regshot/file baselines pre- and post-run to capture persistence and dropped artifacts.
Validation
- The observed process tree and network match the static-analysis hypothesis.
- Persistence mechanisms found dynamically are confirmed in registry/task artifacts.
- Re-running from the clean snapshot reproduces the core behavior.
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.
- 8d ago First seen · 104 lines · 68 tokens per session scan A 8ac9ead8d045
performing-dynamic-analysis-in-a-sandbox is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 811 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 2026-09-03.
Other skills, from other repositories
dynamic-malware-analysis
Execute and analyze malware samples within a highly controlled, instrumented sandbox environment to observe their true behavior, network communications, file system modifications, and registry changes in real-time.
dynamic-malware-analysis
Execute and analyze malware samples within a highly controlled, instrumented sandbox environment to observe their true behavior, network communications, file system modifications, and registry changes in real-time.
analyzing-malware-behavior-with-cuckoo-sandbox
Detonate malware samples in Cuckoo Sandbox to observe runtime behavior — process creation, file system and registry changes, network communications, and API calls — and generate behavioral reports for classification and IOC extraction. Use when a sample has passed static triage and needs dynamic/behavioral analysis…
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…
analyzing-linux-elf-malware
Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…