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 zero-lab-ai/skills --skill memory-forensics-triagegit clone --depth 1 https://github.com/zero-lab-ai/skillsWrote 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/zero-lab-ai/skills/memory-forensics-triage)<a href="https://agentmods.dev/skills/zero-lab-ai/skills/memory-forensics-triage"><img src="https://agentmods.dev/badge/skills/zero-lab-ai/skills/memory-forensics-triage/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/zero-lab-ai/skills/memory-forensics-triage"><img src="https://agentmods.dev/badge/skills/zero-lab-ai/skills/memory-forensics-triage.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 | $0.00072 | $0.01030 |
| Opus 5.5 | $0.00029 | $0.00412 |
| Sonnet 5.5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
memory-forensics-triage 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory forensics triage
Memory is a captured vantage, not an infallible narrator. Acquisition changes the system; the acquisition path can be subverted; symbols can be wrong; one image can produce many correlated outputs without becoming multiple independent sources.
This skill analyzes supplied image facts and normalized outputs. It does not acquire memory, provide live collection commands, recover credential material, execute extracted code, query reputation services, or authorize containment.
When to Use
- Triage memory forensics for authorized security work.
- Use only within explicit authorization and the stated rules of engagement.
When NOT to Use
- Do not treat this skill as permission to access, test, or change a target.
- Do not convert missing evidence into a clean result or a stronger claim.
Workflow
- Record written authorization, case and asset identity, platform, image name, size, format, acquisition method and window, tool identity, hash, transfer, custodian, storage, access-log state, acquisition impact, and clock basis.
- Record the analysis engine, version, reported platform or build, selected symbols or profile, match state, validation evidence, and limitations. A successful plugin run does not prove the profile is correct.
- Inventory each supplied observation with its image, source group, artifact class, locator, role, honest time precision, and limitations. Different plugins over one image share one source group.
- Correlate process inventory and lineage, executable regions, modules or mappings, network objects, handles, registry objects, files, credentials, kernel or driver structures, and supplied baselines. Preserve benign alternatives and missing cross-vantage evidence.
- Keep claim types narrow. A connection is a network object, not C2 attribution. An LSASS handle is credential access capability, not credential extraction. A Run value is a persistence mechanism, not proof it executed.
- Use
suspiciousfor mutually reinforcing indicators within one source group. Usecorroboratedonly with at least two independent source groups. Useconfirmedonly when the claim-specific proof requirements in - Track every candidate extraction.
extractedneeds a preserved digest and custody. Malware classification needs analysis of the extracted artifact; bytes that were never recovered cannot be classified. - Build timeline events only from cited times. Keep host-clock time separate from trusted time; unknown skew remains a limitation. Do not assign an exact timestamp to an object merely because the image has an acquisition window.
- Cover all required artifact and case categories. Mark missing work
blockedwith a blocker rather than calling the surface clean. - Record owned, authorization-aware next steps and handoffs. Contact with a live host or external service needs explicit authority beyond offline review.
What ships with it
2 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.
- yesterday First seen · 87 lines · 72 tokens per session scan A 5e91b0f0a1d3
memory-forensics-triage is a skill published in the GitHub repository zero-lab-ai/skills (283 stars, last pushed 12d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,030 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
testing-llm-prompt-injection-and-jailbreaks
Testing LLM-backed applications, chatbots, and AI agents for direct and indirect prompt injection, jailbreaks, system-prompt leakage, and tool/agent abuse during authorized penetration tests, using structured payload families and reliable confirmation signals.
bypassing-authentication-with-forced-browsing
Discovering and accessing unprotected pages, APIs, and administrative interfaces by enumerating URLs and bypassing authentication controls during authorized security assessments.
analyzing-ios-app-security-with-objection
Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem…
conducting-full-scope-red-team-engagement
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.
exploiting-ai-model-file-rce
Testing machine-learning model files and model-loading services for remote code execution caused by insecure deserialization (pickle/PyTorch), unsafe config instantiation (Hydra), archive path traversal, and dangerous layer types during authorized penetration tests of AI/ML pipelines.