Vulnerability assessment
Skill bromso/metapowers/plugins/security/skills/vulnerability-assessment
Identify and classify vulnerabilities across systems and codeFrom its SKILL.md
npx -y skills add bromso/metapowers --skill vulnerability-assessmentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.9 KB, 872 tokens by cl100k_base, as published. Nobody here has run it
Vulnerability Assessment
Identify and classify vulnerabilities across systems and code for "$ARGUMENTS". Map vulnerabilities to affected assets, prioritize by risk, and establish a remediation timeline.
Prerequisites
Read .metapowers/security/$ARGUMENTS/00-govern.md. If this file does not exist, tell the user:
Phase 0 (Govern) has not been completed for "$ARGUMENTS". Run a Govern skill first (e.g.,
/security:security-policy $ARGUMENTS), or use--skip-checksto bypass.
If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/security/$ARGUMENTS/skip-log.md.
Process
-
Define assessment scope:
- Identify systems, applications, and infrastructure in scope
- Determine assessment type: network, application, code, configuration, or comprehensive
- Define boundaries: production only, staging, or all environments
- Establish rules of engagement and assessment window
-
Identify vulnerability sources:
- OWASP Top 10 — map application vulnerabilities against current OWASP Top 10 categories (injection, broken auth, sensitive data exposure, XXE, broken access control, misconfiguration, XSS, insecure deserialization, known vulnerable components, insufficient logging)
- CVE databases — check known vulnerabilities in deployed software versions (NVD, vendor advisories)
- Dependency scans — analyze third-party libraries and packages for known vulnerabilities (npm audit, pip safety, Dependabot, Snyk)
- Code analysis — static analysis (SAST) findings, code review results, secrets in code
- Configuration review — cloud misconfigurations, default credentials, overly permissive permissions, unencrypted storage
-
Classify by CVSS score and exploitability:
- For each vulnerability, record:
- CVE/identifier — CVE number or internal identifier
- CVSS base score (0.0-10.0) and severity (None/Low/Medium/High/Critical)
- Exploitability — is a public exploit available? Is it actively exploited in the wild?
- Attack vector — network, adjacent, local, or physical
- Description — what the vulnerability is and how it can be exploited
- For each vulnerability, record:
-
Map to affected assets:
- Cross-reference each vulnerability with the asset inventory
- Identify which systems, services, and data stores are affected
- Note cascading effects: a vulnerability in a shared component affects all dependent assets
- Highlight vulnerabilities affecting critical or customer-facing assets
-
Prioritize by risk:
- Calculate effective risk: CVSS score x asset criticality modifier
- Critical asset: 1.5x multiplier
- High asset: 1.25x multiplier
- Medium asset: 1.0x multiplier
- Low asset: 0.75x multiplier
- Factor in exploitability: actively exploited vulnerabilities get highest priority regardless of score
- Group into remediation urgency: Immediate (0-48h), Urgent (1-2 weeks), Planned (30 days), Scheduled (90 days)
- Calculate effective risk: CVSS score x asset criticality modifier
-
Write the artifact to
.metapowers/security/$ARGUMENTS/01-identify.mdwith heading:Vulnerability Assessment
Include sections:
- Assessment Scope — systems assessed and methodology used
- Vulnerability Inventory — all findings with CVE, CVSS, exploitability, and affected assets
- Risk Prioritization — ranked list by effective risk score
- Remediation Timeline — grouped by urgency with target resolution dates
- Trending Analysis — patterns in vulnerability types indicating systemic issues
Output
The vulnerability assessment written to .metapowers/security/$ARGUMENTS/01-identify.md. Present a summary to the user highlighting:
- Total vulnerabilities found by severity level
- Most critical findings requiring immediate attention
- Systemic patterns across vulnerability types
- Recommended remediation timeline and priorities
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most security skills give in 872 tokens
Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07
- Parameterize all database queriesin 68 of 648, across 51 files
- Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
- Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
- Configure security headersin 35 of 648, across 19 files
- Validate all inputsin 32 of 648, across 24 files
- Validate all external input at the system boundaryin 29 of 648, across 19 files
- Run containers as a non-root userin 28 of 648, across 15 files
- Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
- Run dependency audits before every releasein 21 of 648, across 10 files
- Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
- Copy dependencies before source codein 20 of 648, across 9 files
- Store secrets in environment variablesin 20 of 648, across 18 files
Said here and by no other author read
- read govern file before starting
- log skipped checks to file
- define assessment scope and boundaries
- map vulnerabilities to affected assets
- calculate effective risk score
- group findings by remediation urgency
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.