CtrlK
BlogDocsLog inGet started
Tessl Logo

pt-gaining-access

Guides controlled exploitation of validated vulnerabilities to measure real-world impact. Use when the user requests proof-of-concept validation, privilege escalation testing, or attack path confirmation in an authorized environment.

94

1.50x
Quality

92%

Does it follow best practices?

Impact

96%

1.50x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

36%

Customer Portal Security Assessment — Gaining Access Report

Exploitation workflow and structured reporting

Criteria
Without context
With context

In-scope candidate selection

100%

100%

Preconditions documented

100%

100%

Rollback or safety plan

100%

100%

Step-by-step commands recorded

100%

100%

Exploit chain and access level

100%

100%

Output template structure

16%

100%

Tested Vulnerability fields

25%

100%

Business impact in Risk Statement

20%

100%

Handoff completeness

0%

100%

Reproducible evidence

90%

100%

Containment recommendations

70%

100%

97%

34%

Internal Web Server Compromise — Impact Analysis Report

Blast radius assessment and privilege boundary documentation

Criteria
Without context
With context

Reachable systems documented

100%

100%

Reachable data documented

100%

100%

Privilege boundary assessment

80%

70%

Segmentation control evaluation

100%

100%

Exploit chain and access level

62%

100%

Business impact statement

70%

100%

Remediation owners named

12%

100%

Retest criteria specified

0%

100%

Business risk linkage

90%

100%

Output template structure

37%

100%

Impact observed field

0%

100%

91%

26%

Healthcare Portal SQL Injection — Proof of Concept Report

PoC scope boundaries and non-destructive evidence

Criteria
Without context
With context

Non-destructive PoC

100%

100%

Persistence excluded

20%

70%

Minimal payload approach

100%

100%

Exploitable field present

25%

100%

Tested Vulnerability section

37%

100%

Reproducible reproduction steps

100%

100%

Immediate containment recommendations

40%

40%

Output template structure

0%

100%

Authorized scope stated

100%

100%

Business risk linkage

100%

100%

Repository
santosomar/ethical-hacking-agent-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.