CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

vulnerability-scanning

Automated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit. Use for CI/CD security gates, pre-deployment audits, compliance requirements, or encountering CVE detection, outdated packages, license compliance, SBOM generation errors.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and token-efficient, with executable commands and complete CI/script examples throughout. The main gap is workflow clarity: it catalogs tools without a decision sequence, triage interpretation, or remediation loop, so a user is left to assemble the process themselves.

Suggestions

Add a short decision workflow (e.g., dependency change → npm audit/Snyk; container build → trivy image; Python code → bandit) so the tool catalog becomes a sequenced process with explicit validation checkpoints (fail the build only on HIGH/CRITICAL, then triage).

Add a brief section on interpreting and acting on results — triaging findings, suppressing/accepting false positives (the 'Document accepted false positives' bullet currently has no how-to), and remediation basics.

Move the full GitHub Actions workflow and Node.js scanner script into reference files (e.g., references/ci-workflow.md, scripts/security-scan.js) to slim SKILL.md into an overview and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Nearly all content is commands and code with no concept explanations Claude already knows; minor padding remains in generic Best Practices bullets ("Integrate scanning in CI/CD pipeline", "Scan dependencies and containers") and the partially redundant Tools list.

4 / 5

Actionability

Every section provides copy-paste ready material: exact npm/snyk/safety/trivy/bandit commands, a complete GitHub Actions workflow, and a complete Node.js script that parses JSON results, guards against non-JSON output, and exits non-zero on critical findings.

5 / 5

Workflow Clarity

The body is a per-tool command catalog with no sequenced workflow: no guidance on selecting the right scanner for a given situation, triaging or interpreting results, or remediating findings, and validation is only implicit (CI exit-code '1').

3 / 5

Progressive Disclosure

No bundle files exist and the single-file body (~115 lines) is well organized with clear section headers; the full GitHub Actions YAML and Node.js script could arguably move to reference files, which keeps it below the top anchor.

4 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit 'Use for...' trigger clause covering concrete scenarios and tool names. The only weakness is that capability breadth rests on one action verb ('scanning') plus tool names rather than a list of distinct actions.

DimensionReasoningScore

Specificity

Names concrete scan targets ("dependencies, code, containers") and specific tools ("Trivy, Snyk, npm audit") in third-person voice, but "scanning" is the only action verb, so coverage has minor gaps rather than multiple distinct actions.

4 / 5

Completeness

Explicitly answers both what ("Automated security scanning for dependencies, code, containers with Trivy, Snyk, npm audit") and when ("Use for CI/CD security gates, pre-deployment audits, compliance requirements, or encountering CVE detection...") with concrete trigger phrases, matching the top anchor's structure.

5 / 5

Trigger Term Quality

Includes natural phrases users would say such as "CVE detection", "outdated packages", "license compliance", and "pre-deployment audits", though a few common variations like "vulnerability scan" or "Docker scan" are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (dependency/container security scanning) with distinct triggers (CVE, SBOM, Trivy, Snyk, npm audit) that are unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/vulnerability-scanning/skills/vulnerability-scanning/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.