CC ai-red-teaming
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
Run structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Run structured AI red team exercises for jailbreak resistance, data exfiltration
-
low Risky intent
intent-offensive-securitySKILL.md:35Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# AI Red Teaming
-
low Risky intent
intent-offensive-securitySKILL.md:124Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)"""ai_red_team_runner.py - Automated red team test harness."""
quoted -
low Risky intent
intent-offensive-securitySKILL.md:321Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# AI Red Team Report
-
low Risky intent
intent-offensive-securitySKILL.md:404Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- penetration-testing (`penetration-testing`) - Broader offensive security process
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_repo" - note
frontmatter-keyunknown frontmatter key "source_type" - note
frontmatter-keyunknown frontmatter key "date_added" - note
frontmatter-keyunknown frontmatter key "license_source"
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4346 tokens
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 14 top-level sections: this looks like several domains in one skill
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
- +2Single-language instructions
- +3Description length 144: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.