AC ciso-advisor
Security leadership for growth-stage companies. Risk quantification in dollars, compliance roadmap (SOC 2/ISO 27001/HIPAA/GDPR), security architecture strategy, incident response leadership, and board-level security reporting. Use when building security programs, justifying security budget, selecting compliance frameworks, managing incidents, assessing vendor risk, or when user mentions CISO, security strategy, compliance roadmap, zero trust, or board security reporting.
Security leadership for growth-stage companies.
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
AnalyzerSecurityInfrastructureData and analyticstype 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 · 10
✓ No critical or high findings
Medium and low: 10
-
low Risky intent
intent-offensive-securityreferences/incident_response.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| SEV-1 (Critical) | Confirmed breach, data exfil, ransomware, production down | Active ransomware, confirmed data theft, complete service outage | Immediate (< 1 hour) | CEO, board within 24 hrs |
-
low Risky intent
intent-offensive-securityreferences/incident_response.md:22Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Critical distinction for response planning:** A ransomware attack is an incident. If data was exfiltrated before encryption, it's also a breach. Assume breach until proven otherwise.
-
low Risky intent
intent-offensive-securityreferences/incident_response.md:208Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Sample Tabletop Scenario: Ransomware
-
low Risky intent
intent-offensive-securityreferences/incident_response.md:211Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)> It's 6:47 AM on a Monday. Your DevOps engineer receives automated alerts that production databases are inaccessible. By 7:15 AM, they discover a ransomware note demanding $500,000 in Bitcoin. Severa
quoted -
low Risky intent
intent-offensive-securityreferences/incident_response.md:298Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Coverage should include: first-party loss, third-party liability, ransomware, business interruption, regulatory defense
-
low Risky intent
intent-offensive-securityreferences/security_strategy.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Financially motivated criminals | Data theft, ransomware | Phishing, credential stuffing | High |
-
low Risky intent
intent-offensive-securityreferences/security_strategy.md:59Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Direct financial loss**: fraud, ransomware payment, theft
-
low Risky intent
intent-offensive-securityreferences/security_strategy.md:70Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Ransomware attack | $350K | 0.20 | $70,000/yr |
-
low Risky intent
intent-offensive-securityreferences/security_strategy.md:173Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Series B | $10–50M | 3–5% revenue | +ZTNA, Red team, dedicated CISO |
-
low Risky intent
intent-offensive-securityreferences/security_strategy.md:178Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. Automated backups with tested restore (ransomware defense)
Files scanned: 6. 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 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1610 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +2Single-language instructions
- +3Description length 475: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.