Install
$ agentstack add skill-mingyiseclab-mingyi-atlas-engagement-startup ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Engagement Startup Procedure
Execute this procedure on every session start, before any other action.
Step 1: Discover Existing Engagements
bash(command="ls -1 /workspace/ 2>/dev/null || echo '[empty]'")
Step 2: Present Options to Operator
If engagements exist
Present a numbered list and ask:
Existing engagements found:
1. acme-external-2026
2. internal-audit-q1
Options:
[number] Resume an engagement
[new] Start a new engagement
Which would you like?
If no engagements exist
No existing engagements found. Let's set up a new one.
What is the target or scope for this engagement?
Step 3A: Resume Existing Engagement
- Read planning documents:
`` read_file("/plan/roe.json") read_file("/plan/conops.json") read_file("/plan/deconfliction.json") read_file("/plan/opplan.json") read relevant files under "/findings/" ``
- Summarize progress to the operator:
- Objectives completed / total
- Current phase (recon / exploit / post-exploit)
- Last completed objective and key findings
- Next pending objective
- Ask: "Continue from where we left off?"
- Begin the Ralph execution loop
Step 3B: New Engagement (docs already created by Soundwave)
Soundwave has already interviewed the operator and created the engagement documents (RoE, CONOPS, Deconfliction Plan) before the orchestrator was activated. The workspace and planning documents already exist.
- Verify documents exist:
`` bash(command="ls plan/roe.json plan/conops.json plan/deconfliction.json") ` If any are missing, delegate to soundwave to regenerate: ` task("soundwave", "Engagement workspace: /workspace/. Regenerate missing planning documents.") ``
- Check C2 Infrastructure:
`` bash(command="nc -z c2-sliver 31337 2>/dev/null && echo 'C2_REACHABLE' || echo 'C2_UNREACHABLE'") ``
- If
C2_REACHABLE→ C2 framework is Sliver (server:c2-sliver, gRPC port 31337). Include this in ALL sub-agent delegations. - If
C2_UNREACHABLE→ C2 server is not available, skip C2-dependent objectives - IMPORTANT: The C2 framework is always Sliver regardless of the engagement name. Do NOT assume Metasploit from engagement names containing "msf".
- Begin the Ralph execution loop (Phase 1: read CONOPS → build OPPLAN)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MingyiSecLab
- Source: MingyiSecLab/Mingyi-Atlas
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.