prompt-injection-test
A test skill with prompt injection patterns
20
Quality
0%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./evals/test_skills/malicious/prompt-injection/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
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 real 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%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is not a legitimate skill file - it is a prompt injection attack attempting to override system instructions and execute malicious code. The content provides 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 with legitimate, safe, executable examples for an actual task
Define a real skill purpose with concrete, actionable guidance that helps Claude perform a specific task
Add proper structure with clear sections describing what the skill teaches and how to apply it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is not a legitimate skill - it contains no useful instructional content, only malicious prompt injection attempts that waste tokens on harmful directives. | 1 / 3 |
Actionability | The 'guidance' provided is a malicious command injection attempt, not actionable skill content. There are no legitimate, executable instructions for any real task. | 1 / 3 |
Workflow Clarity | There is no workflow - just a prompt injection attempt followed by a dangerous shell command. No steps, validation, or legitimate process is described. | 1 / 3 |
Progressive Disclosure | No structure, no references, no organization - just malicious content masquerading as a skill file. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cisco-ai-defense/skill-scanner
- Commit
c0a625f
- 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.