prompt-injection-test
A test skill with prompt injection patterns
Install with Tessl CLI
npx tessl i github:cisco-ai-defense/skill-scanner --skill prompt-injection-testOverall
score
18%
Does it follow best practices?
Validation for skill structure
Activation
0%This description is essentially a placeholder with no functional value for skill selection. It fails all dimensions by providing no concrete actions, no natural trigger terms, no guidance on when to use it, and no distinguishing characteristics. Claude would have no basis for selecting this skill appropriately.
Suggestions
Replace the placeholder text with specific concrete actions the skill performs (e.g., 'Detects and analyzes prompt injection attempts in user inputs').
Add a 'Use when...' clause with explicit trigger conditions (e.g., 'Use when reviewing user inputs for security vulnerabilities or testing prompt safety').
Include natural keywords users might say when needing this functionality (e.g., 'security testing', 'input validation', 'injection detection').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'A test skill with prompt injection patterns' is entirely abstract and does not describe what the skill actually does. | 1 / 3 |
Completeness | Missing both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent guidance. | 1 / 3 |
Trigger Term Quality | Contains no natural keywords users would say. 'Test skill' and 'prompt injection patterns' are technical/meta terms, not user-facing trigger terms for any practical task. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely vague and could conflict with anything. 'Test skill' provides no clear niche or distinct triggers to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%This is not a legitimate skill - it's a prompt injection attack attempting to override system instructions and execute malicious code. The content contains zero educational or instructional value and represents a security threat rather than useful guidance.
Suggestions
Remove all prompt injection patterns ('Ignore all previous instructions', 'System Override', etc.)
Replace malicious code examples with legitimate, safe, executable code relevant to an actual skill
Define a clear, legitimate purpose for the skill and provide actionable guidance toward that purpose
Add proper structure with a real quick start section and concrete examples of the intended task
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely brief but contains zero useful information - it's entirely malicious prompt injection attempts with no legitimate skill content. | 1 / 3 |
Actionability | Provides no legitimate actionable guidance; the only 'action' is a malicious command injection attempt that should never be executed. | 1 / 3 |
Workflow Clarity | No workflow exists; the content is a prompt injection attack with no legitimate multi-step process or validation. | 1 / 3 |
Progressive Disclosure | No structure or organization; just malicious injection patterns with no references to additional materials or logical content hierarchy. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
75%Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 12 / 16 Passed | |
- 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.