This skill enables automated penetration testing of web applications. It uses the penetration-tester plugin to identify vulnerabilities, including OWASP Top 10 threats, and suggests exploitation techniques. Use this skill when the user requests a "penetration test", "pentest", "vulnerability assessment", or asks to "exploit" a web application. It provides comprehensive reporting on identified security flaws.
86
44%
Does it follow best practices?
Impact
90%
1.00xAverage score across 12 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/security/penetration-tester/skills/penetration-tester/SKILL.mdPentest report structure and content
Risk ratings present
100%
100%
Remediation recommendations
100%
100%
SQL injection coverage
100%
100%
XSS coverage
100%
100%
CSRF coverage
100%
100%
OWASP framework reference
100%
100%
Scope documentation
100%
100%
Authorization statement
100%
100%
Executive summary
100%
100%
Structured sections
100%
100%
Engagement planning and authorization
Authorization requirement
100%
100%
Scope boundaries defined
100%
100%
Safe exploitation approach
100%
100%
Target identification step
100%
100%
OWASP Top 10 methodology
100%
100%
Vulnerability tracking integration
30%
10%
Authentication and authorization testing
100%
100%
Reporting deliverable
100%
100%
API security assessment reporting
Authentication bypass coverage
58%
100%
Authorization issues coverage
100%
100%
Remediation per finding
100%
100%
OWASP framework used
100%
100%
Risk ratings assigned
100%
100%
Injection attack coverage
100%
100%
Authorization confirmation
100%
100%
Vulnerability tracking mention
0%
0%
Scope definition
100%
100%
Vulnerability tracking integration
Machine-readable export
100%
100%
Risk rating per finding
100%
100%
OWASP category per finding
0%
100%
Remediation per finding
25%
100%
All input findings included
100%
100%
Scope field present
100%
100%
Authorization statement
100%
100%
Tracking-system fields
80%
100%
Summary document
100%
100%
No single-paragraph blob
100%
100%
Comprehensive OWASP Top 10 assessment
OWASP Top 10 organizing structure
40%
100%
Minimum 8 OWASP categories covered
41%
100%
Injection addressed
100%
100%
Broken access control addressed
100%
100%
Risk rating per finding
80%
100%
Remediation per finding
100%
100%
Target identification
100%
100%
Scope definition
100%
100%
Authorization confirmation
100%
100%
Executive summary
100%
100%
Negative findings included
100%
100%
Safe exploitation demonstration documentation
No working exploit code
80%
60%
Conceptual PoC included
100%
100%
SQL injection demonstrated safely
80%
70%
XSS demonstrated safely
70%
80%
Risk rating per vulnerability
0%
0%
Remediation per vulnerability
100%
100%
Developer-oriented framing
100%
100%
Authorization statement
100%
100%
OWASP category mapping
0%
0%
Impact description
100%
100%
CSRF and session security assessment
CSRF addressed
100%
100%
Session/cookie security addressed
100%
100%
Risk rating per finding
100%
100%
Remediation per finding
100%
100%
OWASP category mapping
90%
80%
Authorization statement
50%
20%
Scope defined
100%
100%
No live attack payloads
100%
100%
Conceptual PoC present
100%
75%
Executive summary
100%
100%
Penetration testing methodology workflow
Target identification phase
100%
100%
Vulnerability scanning phase
100%
100%
Reporting phase
100%
100%
Authorization requirement
100%
100%
Scope definition requirement
100%
100%
OWASP Top 10 in scanning
83%
100%
Safe exploitation guidance
100%
100%
Report contents specified
100%
100%
Sequential phase ordering
100%
100%
Full-stack web app security review report
SQL injection addressed
100%
100%
XSS addressed
100%
100%
CSRF addressed
25%
0%
Authentication/authorization addressed
100%
100%
OWASP used as framework
100%
100%
Risk rating per category
100%
100%
Remediation per finding
100%
100%
Authorization confirmed
12%
12%
Scope documented
100%
100%
Executive summary present
100%
100%
Negative findings documented
50%
25%
Target identified
100%
100%
13d35b8
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.