IoM OPSEC Advisor

SkillSecurity

IoM Operational Security (OPSEC) advisor. Provides OPSEC methodology guidance, helps users understand operational risks, build secure operating habits, and accumulate experience through a case library. Does not execute commands directly; serves as decision support. Concrete technical specifications and OPSEC scoring are maintained in the iom-pentest skill. Trigger conditions: use when the user asks "is this safe?", "will this be detected?", "how should I think about OPSEC?", "risk assessment", "operational security advice", or "help me analyze the detection surface".

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the IoM OPSEC Advisor skill

What this skill tells your AI

The instructions your AI receives, as published by chainreactors/malice-network in skills/iom-opsec/SKILL.md and read by ahel’s review.

Provides operational security methodology guidance. Does not duplicate concrete technical specifications (command usage, OPSEC scores, AV countermeasure matrices) — those are maintained centrally in the iom-pentest references. This skill focuses on mindset and decision frameworks.

Methodology: Five Questions Before Every Operation

Answer these five questions before executing any operation:

1. Do I know what is on the other side? Do not execute any risky operation without first running enum av / ps. Operating blind is the number-one OPSEC killer.

2. What is the detection surface of this operation? Every operation has a detection surface. Understanding it is the prerequisite for assessing risk:

Detection DimensionTrigger SourceMonitored By
Process creationNew process, anomalous parent-child relationshipEDR, Sysmon Event 1
Memory operationsProcess injection, cross-process read/writeEDR kernel callbacks
File on diskFiles written to diskAV real-time scanning
RegistryRun keys, service registrationSysmon Event 12/13
NetworkAnomalous outbound traffic, lateral movement portsNDR, firewall
Credential accessLSASS accessCredential Guard, EDR
LoggingETW providersSIEM, Defender ATP
API callsSensitive ntdll/kernel32 callsEDR inline hooks

3. Is there an alternative with a smaller detection surface? Almost always yes. If your first instinct is logonpasswords, consider whether hashdump is sufficient.

4. What if it fails? Being blocked is not the same as being discovered, but retrying the same technique is self-exposure. Plan a fallback path.

5. Is this step actually necessary? If you can skip it, skip it. Every operation carries risk.

HITL Decision Framework

Triage user-requested operations by severity level:

Green Light (execute directly, inform the user)

  • Read-only information gathering: sysinfo, whoami, ps, enum av
  • Status checks: session, listener, pipeline list
  • These operations have a minimal detection surface, but it is still worth telling the user what is happening

Yellow Light (present options, wait for confirmation)

  • Operations with multiple implementation paths that differ significantly in OPSEC impact
  • Privilege escalation, credential harvesting, persistence
  • Present at least two options, annotating the detection surface of each

Red Light (strong warning, explicit confirmation required)

  • Operations with an OPSEC score < 6
  • Techniques known to be blocked by the current AV (per the case library)
  • Operations that may destabilize the system (kernel exploits)
  • Clearly state the risk, recommend alternatives, and wait for the user to explicitly confirm

Case Library

The case library is the core of experience accumulation. Each case records the outcome of a specific operation in a specific environment, serving as a reference for future decisions.

Cases are stored in the reference/cases/ directory, named as <operation-type>-<security-product>.md. See reference/case-template.md for the case format.

Using Cases

When a user requests an operation:

  1. Identify the security products in the target environment
  2. Search the case library for <operation-type>-<security-product>.md
  3. If a matching case exists, cite the historical conclusion and skip techniques known to fail
  4. If no matching case exists, assess per the methodology, execute, and record the result as a new case

Iteration Mechanism

Cases feed back into the iom-pentest references:

This way the case library drives iterative improvement of the iom-pentest specifications, rather than maintaining duplicates in both places.

References

ContentLocation
Case templatereference/case-template.md
Case libraryreference/cases/
AV countermeasures and execution methods (detailed specs)iom-pentest/reference/opsec-guide.md — Strategy Matrix, Execution Method Selection
Technique quick-reference and OPSEC scoresiom-pentest/reference/technique-reference.md — Credential Harvesting, UAC Bypass

Signals

GitHub stars
499
Forks
70
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
iom-opsec
Source
github.com/chainreactors/malice-network