CC deliberation-debate-red-teaming
Challenges plans, designs, and decisions from multiple adversarial perspectives to surface blind spots, hidden assumptions, and vulnerabilities before they cause real damage. Use when testing plans or decisions for blind spots, need adversarial review before launch, validating strategy against worst-case scenarios, building consensus through structured debate, identifying attack vectors or vulnerabilities, or when groupthink or confirmation bias may be hiding risks.
Challenges plans, designs, and decisions from multiple adversarial perspectives to surface blind spots, hidden assumptions, and vulnerabilities before they…
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
ProcedureSecurityOperations and projectstype and topics are labelled automatically from the skill text
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 · 15
✓ No critical or high findings
Medium and low: 15
-
low Risky intent
intent-offensive-securityresources/methodology.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Deliberation, Debate & Red Teaming: Advanced Methodology
-
low Risky intent
intent-offensive-securityresources/methodology.md:5Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Copy this checklist for advanced red team scenarios:
-
low Risky intent
intent-offensive-securityresources/methodology.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Advanced Red Teaming Progress:
-
low Risky intent
intent-offensive-securityresources/methodology.md:9Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ ] Step 1: Select appropriate red team technique
-
low Risky intent
intent-offensive-securityresources/methodology.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Step 1: Select appropriate red team technique** - Match technique to proposal complexity and stakes. See [Technique Selection](#technique-selection).
-
low Risky intent
intent-offensive-securityresources/template.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Deliberation, Debate & Red Teaming Template
-
low Risky intent
intent-offensive-securityresources/template.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Red Teaming Progress:
-
low Risky intent
intent-offensive-securityresources/template.md:315Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Key Changes Based on Red Team:**
-
low Risky intent
intent-offensive-securityresources/template.md:341Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Before delivering red team analysis, verify:
-
low Risky intent
intent-offensive-securityresources/template.md:362Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- [ ] Changes clearly linked to risks identified in red team
detector -
low Risky intent
intent-offensive-securitySKILL.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Deliberation, Debate & Red Teaming
-
low Risky intent
intent-offensive-securitySKILL.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Deliberation & Red Teaming Progress:
-
low Risky intent
intent-offensive-securitySKILL.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)For each role, generate specific critiques: What could go wrong? What assumptions are questionable? What edge cases break this? Be adversarial but realistic (steelman, not strawman arguments). For adv
detector -
low Risky intent
intent-offensive-securitySKILL.md:201Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Skip red teaming if:**
-
low Risky intent
intent-offensive-securitySKILL.md:204Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Already thoroughly vetted (extensive prior review, red team would be redundant)
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 85Steps. 83 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2461 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
- +1No license
- +2Single-language instructions
- +3Description length 470: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 83 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.