CB performing-soc-tabletop-exercise
Performs tabletop exercises for SOC teams simulating security incidents through discussion-based scenarios to test incident response procedures, communication workflows, and decision-making under pressure without impacting production systems. Use when organizations need to validate IR playbooks, train analysts, or meet compliance requirements for incident response testing.
Performs tabletop exercises for SOC teams simulating security incidents through discussion-based scenarios to test incident response procedures, communication…
As a process B 69/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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 · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:18Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- **Parameters**: `scenario_type` (str) - one of `ransomware`, `data_breach`, `supply_chain`; `participants` (list[dict]) - role/count pairs
quoted -
low Risky intent
intent-offensive-securityreferences/api-reference.md:40Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)| `ransomware` | 6 injects | Detection, containment, ransom decision, recovery |
table -
low Risky intent
intent-offensive-securityreferences/api-reference.md:42Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `supply_chain` | 4 injects | Vendor compromise, lateral movement, credential reset |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:61Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)"strengths": ["Ransomware indicators correctly identified"]
detector -
low Risky intent
intent-offensive-securitySKILL.md:64Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)title: "Operation Dark Harvest — Ransomware Attack Scenario"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)1: "Test SOC team's ability to detect and triage ransomware indicators"
detector -
low Risky intent
intent-offensive-securitySKILL.md:142Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- "This is now a confirmed ransomware incident. What is your incident classification?"
quoted -
low Risky intent
intent-offensive-securitySKILL.md:173Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Attacker had access for 5 days before deploying ransomware
-
low Risky intent
intent-offensive-securitySKILL.md:176Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- The ransomware variant is identified as LockBit 3.0
Files scanned: 4. 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 "mitre_attack" - note
frontmatter-keyunknown frontmatter key "nist_csf"
Process rating: all ten parameters 69/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4012 tokens
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 375: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.