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 trilwu/secskills --skill analyzing-memory-imagesgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/trilwu/secskills/analyzing-memory-images)<a href="https://agentmods.dev/skills/trilwu/secskills/analyzing-memory-images"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/analyzing-memory-images/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/trilwu/secskills/analyzing-memory-images"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/analyzing-memory-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high YARA Match · line 176 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.
- medium Privilege Escalation · line 38 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 40 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00081 | $0.03938 |
| Opus 5 | $0.00041 | $0.01969 |
| Sonnet 5 | $0.00016 | $0.00788 |
| Haiku 4.5 | $0.00008 | $0.00394 |
Grade B, and why
analyzing-memory-images scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo insmod lime-$(uname -r).ko "path=/evidence/mem.lime format=lime" Copies of this mod
1 near-identical copy found in the catalogue:
- analyzing-memory-images — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyzing Memory Images
Memory is the only place certain artifacts exist — injected code, decrypted payloads, credential material, and network connections from processes that have already exited. Disk forensics misses all of these. The work is getting the image before it is lost, then asking the right questions in the right order.
When to Use
- You have a memory dump (raw, LiME, EWF, crash dump, or VM snapshot) to analyze
- Investigating a compromised host and need artifacts that exist only in RAM
- Looking for injected code, process hollowing, or reflective DLL loading
- Extracting credential material — hashes, Kerberos tickets, cached credentials
- Identifying network connections and listening ports from a point-in-time capture
- Detecting kernel-level rootkits — SSDT hooks, DKOM, hidden drivers
When NOT to Use
- Broader incident response methodology — use
responding-to-incidents - You have an acquired disk image, not a RAM capture — use
analyzing-disk-images - On-disk artifacts of a live/triage Windows host — use
investigating-windows-endpoints - Analyzing a known malware sample on disk — use
analyzing-malware - Writing detection rules from your memory findings — use
engineering-detections
Acquisition
Acquire memory before doing anything else on a live system. Every command you run on the box changes what is in memory. Image first, triage second.
# Linux — LiME (kernel module, minimal footprint)
sudo insmod lime-$(uname -r).ko "path=/evidence/mem.lime format=lime"
# Alternative: AVML (no kernel module needed, userspace)
sudo ./avml /evidence/mem.lime
# Windows — WinPMem (signed driver)
winpmem_mini_x64.exe mem.raw
# Alternative: DumpIt (single executable, click-to-run for non-technical staff)
DumpIt.exe /OUTPUT mem.raw /QUIET
# macOS — osxpmem is dead (Rekall archived, last release 2017, Intel-only, and
# blocked by SIP/kext restrictions on Big Sur+ and all Apple Silicon). Full-RAM
# capture on a modern Mac needs commercial tooling with Apple entitlements
# (e.g. Volexity Surge Collect); otherwise take process-scoped dumps and
# record that physical memory was not obtainable. See responding-to-incidents.
# VM snapshots — no agent needed
# VMware: .vmem file alongside the .vmx (suspend the VM first for consistency)
# Hyper-V: checkpoint creates .bin and .vsv in the snapshot directory
# KVM/QEMU: virsh dump <domain> mem.raw --memory-only
# VirtualBox: VBoxManage debugvm <name> dumpvmcore --filename mem.elf
# Crash dumps — partial but sometimes all you have
# Windows: %SystemRoot%\MEMORY.DMP (complete dump), or minidumps
# Linux: /var/crash/, kdump output, /proc/kcore (live, pseudo-file)
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 · 384 lines · 81 tokens per session scan B 480b131ba124
analyzing-memory-images is a skill published in the GitHub repository trilwu/secskills (137 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 3,938 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
comet-memory
A review step for deciding whether information should become durable personal memory. It can keep, update, forget, or skip memory candidates based on bounded evidence.
recall-memory
Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.
agent-expert-creation
Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
self-improve
Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…