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 MingyiSecLab/Mingyi-Atlas --skill post-exploit-reportinggit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/post-exploit-reporting)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/post-exploit-reporting"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/post-exploit-reporting/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/mingyiseclab/mingyi-atlas/post-exploit-reporting"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/post-exploit-reporting.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 | $0.00038 | $0.05826 |
| Opus 5 | $0.00019 | $0.02913 |
| Sonnet 5 | $0.00008 | $0.01165 |
| Haiku 4.5 | $0.00004 | $0.00583 |
Grade B, and why
post-exploit-reporting 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
3. Extract credentials with pypykatz: Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 549 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-Exploitation Reporting Knowledge Base
Post-exploitation findings require richer documentation than reconnaissance findings because they demonstrate real-world impact, test Blue Team detection capabilities, and map the full kill chain traversal. This skill provides phase-specific templates and detection gap analysis guidance aligned with PTES, CREST, and TIBER-EU standards.
All agent-authored documents MUST be Markdown format (.md). Operational data files (creds/*.json, network_map.json) are exceptions.
1. Phase-Specific Finding Templates
Each post-exploitation phase has a specialized template. All templates share the same YAML frontmatter schema but differ in body sections to capture phase-relevant details.
A. Credential Access Finding (TA0006)
---
id: FIND-007
severity: high
cvss_score: 8.4
cvss_vector: "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:N/SA:N"
cwe: CWE-522
mitre: [T1003.001]
affected_target: "WEB01 (10.0.0.5)"
affected_component: "LSASS process memory"
confidence: verified
objective_id: OBJ-004
phase: post-exploit
agent: postexploit
detected: false
remediation_priority: immediate
discovered_at: "2026-04-06T16:45:00Z"
---
# [HIGH] LSASS Memory Dump on WEB01 exposes Domain Credentials
## Description
LSASS process memory was dumped on WEB01 (10.0.0.5) using nanodump, yielding NTLM hashes for 3 domain accounts including a service account with Domain Admin group membership.
## Steps to Reproduce
1. From SYSTEM shell on WEB01:
```
nanodump --write C:\Windows\Temp\debug.dmp --valid
```
2. Transfer dump to attack host:
```
impacket-smbclient //10.0.0.5/C$ -k -no-pass
get Windows/Temp/debug.dmp
```
3. Extract credentials with pypykatz:
```
pypykatz lsa minidump debug.dmp
```
## Credentials Obtained
| Username | Type | Hash/Value | Source Host | Domain | Privilege |
|----------|------|-----------|-------------|--------|-----------|
| svc_sql | NTLM | aad3b435...7cb | WEB01 | corp.local | Domain Admin |
| jdoe | NTLM | e19ccf75...2a1 | WEB01 | corp.local | Domain User |
| web_app | NTLM | 31d6cfe0...e0d | WEB01 | corp.local | Domain User |
## Impact
The `svc_sql` account is a member of the Domain Admins group. With this NTLM hash, an attacker can perform Pass-the-Hash to gain full control over the Active Directory domain, including all domain-joined systems and data.
## Evidence
| Type | Path | Description |
|------|------|-------------|
| terminal-log | findings/evidence/FIND-007_nanodump.txt | nanodump execution output |
| terminal-log | findings/evidence/FIND-007_pypykatz.txt | pypykatz credential extraction |
## Detection Gap Analysis
| Control | Fired? | Notes |
|---------|--------|-------|
| EDR (CrowdStrike) | No | nanodump evaded userland hooks via direct syscalls |
| SIEM | No | No alert for LSASS access or suspicious process creation |
| Windows Event Log | Partial | Event 4663 logged but not forwarded to SIEM |
| Network monitoring | No | SMB transfer blended with normal traffic |
Blue team detection status: **Not detected**. LSASS access via direct syscalls bypassed EDR userland hooks entirely.
## Remediation
1. Enable Credential Guard to protect LSASS from memory dumps.
2. Configure EDR to monitor kernel-level LSASS access (PPL enforcement).
3. Forward Windows Security Event 4663 (object access) to SIEM with alerting.
4. Review service accounts: `svc_sql` should NOT be Domain Admin — apply least privilege.
## References
- MITRE ATT&CK T1003.001: https://attack.mitre.org/techniques/T1003/001/
- Microsoft Credential Guard: https://learn.microsoft.com/en-us/windows/security/identity-protection/credential-guard/
- CWE-522: https://cwe.mitre.org/data/definitions/522.html
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 · 549 lines · 38 tokens per session scan B 069867c3a53c
post-exploit-reporting is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 5,826 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.