BB threat-assessment-defense-guide
Generate comprehensive cybersecurity threat assessments and defense guides. Use when evaluating threat landscapes, building defense strategies, ransomware protection plans, phishing defense, APT mitigation, supply chain security, or any threat modeling and defense planning.
As a process B 72/100 · Nearly there — weak spots: when it triggers, running it twice
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 · 11
✓ No critical or high findings
Medium and low: 11
-
low Risky intent
intent-offensive-securityREADME.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Send a message like *"Assess ransomware threats for our healthcare organization"* via WhatsApp, Telegram, or Discord, and your OpenClaw agent will:
quoted -
low Risky intent
intent-offensive-securityREADME.md:51Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Ransomware & Extortion
-
low Risky intent
intent-offensive-securityREADME.md:69Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)You: I'm worried about ransomware and phishing at our hospital.
quoted -
low Risky intent
intent-offensive-securityREADME.md:74Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Threats: Ransomware, Phishing
-
low Risky intent
intent-offensive-securityREADME.md:76Offensive-security / dual-use content (legitimate for authorised testing; review intended use)⚠️ Critical: Healthcare is #1 ransomware target
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Generate comprehensive cybersecurity threat assessments and defense guides for threat landscape evaluation, defense strategy planning, ransomware protection, phishing defense, APT mitigation, supply c
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Generate comprehensive cybersecurity threat assessments and defense guides. Use when evaluating threat landscapes, building defense strategies, ransomware protection plans, phishing defen
-
low Risky intent
intent-offensive-securitySKILL.md:32Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- User mentions ransomware, phishing, APT, DDoS, or other threat types
-
low Risky intent
intent-offensive-securitySKILL.md:61Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- What **threat types** concern them (e.g., Ransomware, Phishing, APT, DDoS, Insider Threat, Supply Chain Attack, Zero-Day Exploits, Social Engineering, Data Exfiltration, Cloud Security Threats)
-
low Risky intent
intent-offensive-securitySKILL.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)"threat_type": ["Ransomware", "Phishing"],
quoted -
low Risky intent
intent-offensive-securitySKILL.md:153Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)**User:** "I'm worried about ransomware attacks on our hospital's systems. Can you assess the threat and tell me how to defend against it?"
quoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 72/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 63 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1948 tokens
- 100Progress reporting. Reports progress
- low 12 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)
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 274: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 63 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
External checks
ClawHub: suspicious
This skill is a legitimate-looking ToolWeb API wrapper, but it can send sensitive security-planning details to a third party without a clear consent step.
LLM: suspicious (high) · VirusTotal: · 29 May 2026