DC conducting-full-scope-red-team-engagement
Plan and execute a comprehensive, MITRE ATT&CK-aligned red team engagement spanning threat modeling, reconnaissance, initial access, and post-exploitation to evaluate an organization's detection, prevention, and response against APT-style behavior. Use when scoping or running a full-scope, objective-based engagement, or purple-teaming against a specific threat actor's TTPs.
Plan and execute a comprehensive, MITRE ATT&CK-aligned red team engagement spanning threat modeling, reconnaissance, initial access, and post-exploitation to…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 23
✓ No critical or high findings
Medium and low: 23
-
low Risky intent
intent-offensive-securityassets/template.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team Engagement Report Template
-
low Risky intent
intent-offensive-securityassets/template.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)[Organization Name] engaged [Red Team Company] to conduct a full-scope red team assessment from [start date] to [end date]. The engagement simulated the tactics, techniques, and procedures (TTPs) of [
detector -
low Risky intent
intent-offensive-securityassets/template.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)The red team achieved [X of Y] defined objectives, with [Z]% of activities detected by the security operations center. Critical gaps were identified in [area 1], [area 2], and [area 3].
-
low Risky intent
intent-offensive-securityassets/template.md:90Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Day 13-20: Post-exploitation, lateral movement, persistence
-
low Risky intent
intent-offensive-securityassets/template.md:132Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### 3.5 Phase 4: Lateral Movement
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Full-Scope Red Team Engagement — API Reference
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:28Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Post-exploitation | 5-7 days | Lateral movement, persistence, privilege escalation |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [PTES Standard](http://www.pentest-standard.org/)
-
low Risky intent
intent-offensive-securityreferences/standards.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Standards and References: Full-Scope Red Team Engagement
-
low Risky intent
intent-offensive-securityreferences/standards.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Privilege Escalation (TA0004)
-
low Risky intent
intent-offensive-securityreferences/standards.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **T1068** - Exploitation for Privilege Escalation
-
low Risky intent
intent-offensive-securityreferences/standards.md:57Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **T1003.001** - OS Credential Dumping: LSASS Memory
-
low Risky intent
intent-offensive-securityreferences/standards.md:58Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **T1003.006** - OS Credential Dumping: DCSync
-
low Risky intent
intent-offensive-securityreferences/workflows.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Workflows: Full-Scope Red Team Engagement
-
low Risky intent
intent-offensive-securityreferences/workflows.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ RED TEAM ENGAGEMENT LIFECYCLE │
-
low Risky intent
intent-offensive-securityreferences/workflows.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ ├── Execute phishing campaign (T1566) │
-
low Risky intent
intent-offensive-securityreferences/workflows.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ ├── Privilege escalation │
-
low Risky intent
intent-offensive-securityreferences/workflows.md:56Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ ├── Credential harvesting │
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Plan and execute a comprehensive, MITRE ATT&CK-aligned red team engagement spanning threat modeling, reconnaissance, initial access, and post-exploitation to evaluate an organization's de
-
low Risky intent
intent-offensive-securitySKILL.md:34Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Conducting Full-Scope Red Team Engagement
-
low Risky intent
intent-offensive-securitySKILL.md:38Offensive-security / dual-use content (legitimate for authorised testing; review intended use)A full-scope red team engagement simulates real-world adversary behavior across all phases of the cyber kill chain — from initial reconnaissance through data exfiltration — to evaluate an organization
-
low Risky intent
intent-offensive-securitySKILL.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- When conducting security assessments that involve conducting full scope red team engagement
-
low Risky intent
intent-offensive-securitySKILL.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Red team infrastructure: C2 servers, redirectors, phishing domains, payload development environment
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1725 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 376: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.