CB performing-purple-team-exercise
Performs purple team exercises by coordinating red team adversary emulation with blue team detection validation using MITRE ATT&CK-mapped attack scenarios, real-time detection testing, and collaborative gap remediation. Use when SOC teams need to validate detection capabilities, improve analyst skills, and close detection gaps through structured offensive-defensive collaboration.
Performs purple team exercises by coordinating red team adversary emulation with blue team detection validation using MITRE ATT&CK-mapped attack scenarios…
As a process B 65/100 · Nearly there — weak spots: failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Dangerous commands
cmd-pipe-to-shellreferences/api-reference.md:7Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)IEX (IWR 'https://raw.githubusercontent.com/redcanaryco/invoke-atomicredteam/master/inst…ps1')
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:120Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)IEX (IWR 'https://raw.githubusercontent.com/redcanaryco/invoke-atomicredteam/master/inst…ps1' -UseBasicParsing)
security skill -
low Risky intent
intent-offensive-securityreferences/api-reference.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Atomic Red Team (PowerShell)
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:42Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `subprocess` | stdlib | Execute Atomic Red Team tests |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Atomic Red Team: https://github.com/redcanaryco/atomic-red-team
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: 'Performs purple team exercises by coordinating red team adversary emulation
quoted -
low Risky intent
intent-offensive-securitySKILL.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Red team assessments produced findings that need translation into detection improvements
-
low Risky intent
intent-offensive-securitySKILL.md:51Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Do not use** for unannounced red team engagements — purple team exercises require explicit coordination between offensive and defensive teams with real-time collaboration.
-
low Risky intent
intent-offensive-securitySKILL.md:55Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Red team capability: internal team or contracted purple team operator
-
low Risky intent
intent-offensive-securitySKILL.md:56Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Attack simulation tools: Atomic Red Team, MITRE Caldera, or C2 framework (authorized)
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 "d3fend_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 65/100
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3049 tokens
- 100Progress reporting. Reports progress
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 382: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.