DD security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR…
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: RA-Skills
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 35
✓ No critical or high findings
Medium and low: 35
-
low Risky intent
intent-offensive-securityexamples/incident-response-template.md:171Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)| 2 | Update incident response playbook with ransomware procedures | Security Manager | 2025-02-01 | High | Open |
fixture -
low Risky intent
intent-offensive-securityexamples/incident-response-template.md:229Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; test fixture / example file)[Detailed technical analysis, IoCs, malware analysis, etc.]
detectorfixture -
low Risky intent
intent-offensive-securityREADME.md:107Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)**Situation**: Your SOC detected ransomware on multiple systems.
detector -
low Risky intent
intent-offensive-securityREADME.md:111Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. Use IR playbook for ransomware (included in security-operations.md)
-
low Risky intent
intent-offensive-securityREADME.md:220Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Ransomware Attack on Production Infrastructure: $900,000
-
low Risky intent
intent-offensive-securityREADME.md:286Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Segment networks to limit lateral movement
-
low Risky intent
intent-offensive-securityREADME.md:430Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- OSCP (Offensive Security Certified Professional)
-
low Risky intent
intent-offensive-securityreference/application-security.md:45Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ □ Penetration testing │
-
low Risky intent
intent-offensive-securityreference/application-security.md:70Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ □ Periodic penetration testing (annually) │
-
low Dangerous commands
cmd-eval-dynamicreference/application-security.md:209Dynamic code execution from decoded/untrusted input (documentation of a security skill)result = os.system(f'ping -c 1 {host}')security skill -
low Secrets in code
secret-high-entropy-tokenreference/application-security.md:494High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)integrity="sha3…kM6+R9GqQ8K/uxy9…8wC"
quoted -
low Risky intent
intent-offensive-securityreference/application-security.md:562Offensive-security / dual-use content (legitimate for authorised testing; review intended use)□ Privilege escalation attempts
-
low Risky intent
intent-offensive-securityreference/compliance-frameworks.md:1093Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Threat: Ransomware Attack
-
low Risky intent
intent-offensive-securityreference/compliance-frameworks.md:1097Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Likelihood: High (0.9) - Widespread ransomware campaigns targeting healthcare
-
low Risky intent
intent-offensive-securityreference/compliance-frameworks.md:1203Offensive-security / dual-use content (legitimate for authorised testing; review intended use)• Perform penetration testing (annually + after significant changes)
-
low Risky intent
intent-offensive-securityreference/security-architecture.md:206Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Limits lateral movement
-
low Risky intent
intent-offensive-securityreference/security-architecture.md:284Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Lateral movement | Possible | Prevented |
-
low Secrets in code
secret-aws-keyreference/security-architecture.md:361AWS access key ID (placeholder value)aws iam update-access-key --access-key-id AKIA…PLE --status Inactive
placeholder -
low Risky intent
intent-offensive-securityreference/security-operations.md:24Offensive-security / dual-use content (legitimate for authorised testing; review intended use)├─ Advanced forensics and malware analysis
-
low Risky intent
intent-offensive-securityreference/security-operations.md:226Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Hunt 3: WMIC used for lateral movement
-
low Risky intent
intent-offensive-securityreference/security-operations.md:308Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| P0 - Critical | Active breach, data exfiltration, ransomware | Active data theft, ransomware encryption, complete system compromise | Immediate (24/7) |
-
low Dangerous commands
cmd-cron-mentionreference/security-operations.md:419Mentions editing / listing crontab (documentation of a security skill)crontab -e # Remove malicious line
security skill -
low Risky intent
intent-offensive-securityreference/security-operations.md:573Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Isolation prevented lateral movement
-
low Risky intent
intent-offensive-securityreference/security-operations.md:579Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Incident response playbook for ransomware needed update
-
low Risky intent
intent-offensive-securityreference/threat-modeling-risk.md:39Offensive-security / dual-use content (legitimate for authorised testing; review intended use)• Examples: Privilege escalation, exploiting vulnerabilities, bypassing access controls
-
low Risky intent
intent-offensive-securityreference/threat-modeling-risk.md:135Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration test results
-
low Risky intent
intent-offensive-securityreference/threat-modeling-risk.md:147Offensive-security / dual-use content (legitimate for authorised testing; review intended use)│ └─ Bypass WAF
-
low Risky intent
intent-offensive-securityreference/threat-modeling-risk.md:341Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Example: Assess risk of ransomware attack
-
low Risky intent
intent-offensive-securityreference/threat-modeling-risk.md:617Offensive-security / dual-use content (legitimate for authorised testing; review intended use)6. Privilege Escalation
-
low Risky intent
intent-offensive-securitySKILL.md:104Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- Perform vulnerability scanning and penetration testing
detector -
low Risky intent
intent-offensive-securitySKILL.md:115Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration test reports
-
low Risky intent
intent-offensive-securitySKILL.md:325Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Ransomware encryption in progress
-
low Risky intent
intent-offensive-securitySKILL.md:437Offensive-security / dual-use content (legitimate for authorised testing; review intended use)□ Penetration test results (for high/critical)
-
low Risky intent
intent-offensive-securitySKILL.md:573Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Penetration testing and red teaming
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7112 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
- 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
- 30Running it twice. 8 mutating operations with no state check
- 70Execution cost. Instruction body is 7112 tokens
- 85Steps. 330 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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
- -45 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 308: enough signal without eating the budget
- +4Structure: 82 headings
- +3Step-by-step instructions: 330 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.