This skill automates security vulnerability testing. It is triggered when the user requests security assessments, penetration tests, or vulnerability scans. The skill covers OWASP Top 10 vulnerabilities, SQL injection, XSS, CSRF, authentication issues, and authorization flaws. Use this skill when the user mentions "security test", "vulnerability scan", "OWASP", "SQL injection", "XSS", "CSRF", "authentication", or "authorization" in the context of application or API testing.
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill performing-security-testing88
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 93%
↑ 1.03xAgent success when using this skill
Validation for skill structure
Security vulnerability report generation
OWASP Top 10 coverage
100%
100%
SQL injection section
100%
100%
XSS section
100%
100%
CSRF section
100%
100%
Authentication assessment
100%
100%
Authorization assessment
100%
100%
Severity ratings present
100%
100%
Remediation steps present
100%
100%
Scope defined
100%
100%
Auth credentials referenced
0%
100%
Without context: $0.3905 · 4m 50s · 10 turns · 11 in / 9,534 out tokens
With context: $0.7183 · 4m 29s · 25 turns · 22 in / 13,484 out tokens
CI/CD security integration and scheduling
Triggered on code changes
100%
100%
Scheduled recurring runs
100%
100%
OWASP coverage mentioned
100%
100%
Injection/XSS/CSRF coverage
75%
100%
Auth/authz coverage
100%
100%
Reporting tool integration
100%
100%
Results pushed to reporting tool
100%
100%
Fail on high severity
100%
100%
Testing strategy documented
100%
100%
Scope of testing defined
80%
100%
Without context: $0.4851 · 3m 38s · 20 turns · 20 in / 8,846 out tokens
With context: $0.5810 · 3m 37s · 24 turns · 24 in / 9,794 out tokens
Scoped API security test planning
Scope defined by module
100%
100%
Scope excludes out-of-scope items
100%
100%
OWASP Top 10 referenced
100%
100%
SQL injection test cases
100%
100%
XSS test cases
77%
100%
CSRF test cases
22%
0%
Authentication test cases
100%
100%
Authorization test cases
100%
100%
Credential handling documented
100%
100%
Findings documentation process
100%
100%
Severity ratings included
100%
100%
Without context: $0.2453 · 2m 12s · 8 turns · 9 in / 6,245 out tokens
With context: $0.6218 · 4m 20s · 23 turns · 104 in / 12,163 out tokens
Source code security audit
SQL injection identified
100%
100%
XSS vulnerability identified
100%
100%
Auth weakness identified
100%
100%
Authorization flaw identified
100%
100%
CSRF risk noted
100%
100%
OWASP Top 10 framework used
100%
100%
Severity ratings on all findings
100%
100%
Remediation steps present
100%
100%
Scope statement included
100%
100%
Debug mode risk flagged
100%
100%
Without context: $0.3103 · 2m 31s · 11 turns · 12 in / 6,243 out tokens
With context: $0.4438 · 3m 8s · 19 turns · 19 in / 7,894 out tokens
Centralized vulnerability management setup
Centralized reporting tool named
50%
41%
Findings pushed to central tool
100%
100%
Regular scan schedule defined
100%
100%
Scope per service documented
90%
70%
Credential handling addressed
100%
100%
OWASP Top 10 coverage required
75%
75%
Injection/XSS/CSRF coverage required
12%
37%
Auth/authz coverage required
25%
25%
Severity normalization addressed
100%
100%
New vulnerability detection goal
100%
66%
Onboarding checklist complete
100%
100%
Without context: $0.3286 · 3m 27s · 13 turns · 16 in / 7,385 out tokens
With context: $0.3678 · 3m 8s · 16 turns · 16 in / 7,572 out tokens
JWT authentication security assessment
JWT tampering risk identified
100%
100%
No token revocation flagged
100%
100%
Long token expiry flagged
100%
100%
IDOR / authorization flaw identified
100%
100%
Weak password policy flagged
100%
100%
Authentication assessment section
62%
62%
Authorization assessment section
62%
62%
Severity ratings on all findings
100%
100%
Remediation steps present
100%
100%
Scope defined
100%
100%
Test credentials documented
37%
50%
Without context: $0.3630 · 3m 22s · 12 turns · 13 in / 7,812 out tokens
With context: $0.6034 · 4m 25s · 27 turns · 788 in / 8,680 out tokens
Cryptographic failures and sensitive data exposure assessment
Cryptographic failure identified
100%
100%
Plaintext sensitive data identified
100%
100%
Weak encryption flagged
100%
100%
OWASP Top 10 framework used
100%
100%
SQL injection covered
100%
100%
XSS covered
100%
100%
CSRF covered
0%
100%
Authentication section present
100%
100%
Authorization section present
71%
100%
Severity ratings on all findings
100%
100%
Remediation steps for all findings
100%
100%
Scope defined
100%
100%
Test credentials documented
0%
0%
Without context: $0.5108 · 6m 27s · 17 turns · 18 in / 9,743 out tokens
With context: $0.4813 · 3m 3s · 20 turns · 53 in / 8,013 out tokens
Vulnerable and outdated dependency security assessment
Vulnerable dependencies identified
100%
100%
CVE or vulnerability details provided
100%
100%
OWASP A06 referenced
100%
100%
OWASP Top 10 framework used
100%
100%
SQL injection covered
100%
100%
XSS covered
100%
100%
CSRF covered
0%
100%
Authentication coverage
100%
100%
Authorization coverage
100%
100%
Severity ratings on all findings
100%
100%
Remediation steps present
100%
100%
Scope defined
100%
100%
Test credentials documented
20%
0%
Without context: $0.4683 · 3m 30s · 13 turns · 14 in / 10,555 out tokens
With context: $0.5665 · 3m 51s · 19 turns · 20 in / 10,819 out tokens
Security logging and monitoring gap assessment
Missing auth failure logging identified
80%
100%
Missing privilege event logging identified
70%
60%
No intrusion detection flagged
62%
75%
OWASP A09 referenced
100%
100%
OWASP Top 10 framework used
100%
100%
SQL injection covered
100%
100%
XSS covered
100%
100%
CSRF covered
100%
100%
Authentication section present
100%
100%
Authorization section present
100%
100%
Severity ratings on all findings
100%
100%
Remediation steps present
90%
100%
Scope defined
100%
100%
Test credentials documented
0%
0%
Without context: $0.3894 · 3m 29s · 16 turns · 17 in / 7,239 out tokens
With context: $0.4408 · 3m 7s · 19 turns · 276 in / 7,210 out tokens
Table of Contents
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.