BD afrexai-cybersecurity-engine
Complete cybersecurity assessment, threat modeling, and hardening system. Use when conducting security audits, threat modeling, penetration testing, incident response, or building security programs from scratch. Works with any stack — zero external dependencies.
Complete cybersecurity assessment, threat modeling, and hardening system.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
AnalyzerAWSInfrastructureSecurityData and analyticstype and topics are labelled automatically from the skill text
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7
✓ No critical or high findings
Medium and low: 7
-
low Risky intent
intent-offensive-securityREADME.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Complete cybersecurity assessment, threat modeling, penetration testing, and security program design — all in one agent skill. Zero external dependencies.
-
low Risky intent
intent-offensive-securityREADME.md:47Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 10 | Penetration Testing | Recon, 4-phase testing, report template |
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Complete cybersecurity assessment, threat modeling, and hardening system. Use when conducting security audits, threat modeling, penetration testing, incident response, or building securit
-
low Risky intent
intent-offensive-securitySKILL.md:119Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **E**levation of Privilege | Can someone gain unauthorized access? | IDOR, broken access control, privilege escalation |
-
low Risky intent
intent-offensive-securitySKILL.md:461Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Penetration test | Quarterly | Manual + automated |
-
low Risky intent
intent-offensive-securitySKILL.md:462Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Red team | Annually | External firm |
-
low Risky intent
intent-offensive-securitySKILL.md:508Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. Verify no lateral movement occurred
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8243 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Execution cost. Instruction body is 8243 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 78 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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
- +1No license
- +2Single-language instructions
- +3Description length 262: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (38 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.