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 detecting-process-injection-in-memorygit 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/detecting-process-injection-in-memory)<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/detecting-process-injection-in-memory"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/detecting-process-injection-in-memory/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/detecting-process-injection-in-memory"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/detecting-process-injection-in-memory.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 | $0.00070 | $0.00714 |
| Opus 5 | $0.00035 | $0.00357 |
| Sonnet 5 | $0.00014 | $0.00143 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
detecting-process-injection-in-memory 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.
What it actually says
Detecting Process Injection in Memory
When to Use
- You have a Windows memory image and want to find injected/hollowed code.
- You are triaging private RWX regions, unbacked executable memory, and PE headers in private allocations (classic injection/hollowing signs).
Do not use this on a live production host without authorization — work from an acquired image. This skill interprets analysis output; run Volatility separately on the image.
Prerequisites
- A memory image and Volatility 3 (
windows.malfind,windows.vadinfo) installed.
Safety & Handling
- Treat carved injected regions as live malicious code; store them password-protected.
Workflow
Step 1: Run malfind and capture output
vol -f memory.raw windows.malfind > malfind.txt
Step 2: Score injection candidates
python scripts/analyst.py score malfind.txt
Flags regions with PAGE_EXECUTE_READWRITE, MZ/PE headers in private memory, and shellcode-like
disassembly hints, ranking processes by suspicion.
Step 3: Corroborate
Cross-check flagged PIDs with windows.vadinfo (private, executable, no mapped file) and the
process tree for anomalous parents.
Step 4: Carve and route
Carve the injected region for follow-on shellcode/PE recovery and analysis.
Validation
- Flagged regions are private + executable, not legitimate mapped images.
- PE-in-private-memory findings are confirmed by an MZ/
This programsignature. - High-scoring PIDs corroborate with VAD protections and process-tree anomalies.
Pitfalls
- JIT engines (.NET, Java, browsers) legitimately create RWX regions — corroborate before alerting.
- Relying on malfind alone; pair with vadinfo and ldrmodules.
- Missing hollowing where the region is RX (not RWX) after protection change.
References
- See
references/api-reference.mdfor the scorer. - ATT&CK T1055 and Volatility 3 docs (linked in frontmatter).
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.
- 9d ago First seen · 93 lines · 70 tokens per session scan A 39e961bf3cd7
detecting-process-injection-in-memory is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 714 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
conducting-memory-forensics-with-volatility
Performs memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests…
conducting-memory-forensics-with-volatility
Use when performing memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for…
volatility-memory-forensics
Analyze full RAM captures (memory dumps) to extract forensic artifacts, detect stealthy malware, recover injected shellcode, and identify rootkits that bypass traditional disk-based antivirus scanning. Use this skill during Incident Response and advanced threat hunting engagements to identify what was actively running…
conducting-memory-forensics-with-volatility
Performs memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests…
conducting-memory-forensics-with-volatility
Performs memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests…
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…