DD llm-testing
(no description)
Not recommendedlow grade D
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Add a description to the frontmatter: without it the skill never triggers.
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 9
✓ No critical or high findings
Medium and low: 9
-
low Risky intent
intent-offensive-securityREADME.md:57Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Red Team Operation Simulations:** Creating scenarios where the LLM needs to propose hypothetical red team strategies for educational purposes, ensuring it provides information in a way that's alig
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Provides curated prompts to test LLM security, bias, privacy, alignment, and robustness for authorized AI safety and red team assessments. <br>
-
low Risky intent
intent-offensive-securityskill-card.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Security researchers, AI safety engineers, and red team operators use this skill to evaluate LLM behavior for bias, privacy leakage, alignment bypasses, and adversarial prompt resistance in authorized
-
low Risky intent
intent-offensive-securityskill-card.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [AI Red Teaming Best Practices](https://www.anthropic.com/index/red-teaming-language-models) <br>
-
low Risky intent
intent-offensive-securitySKILL.md:9Offensive-security / dual-use content (legitimate for authorised testing; review intended use)This skill is designed for security researchers, AI safety engineers, and red team operators to assess LLM vulnerabilities and ensure models:
-
low Risky intent
intent-offensive-securitySKILL.md:19Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Security Auditing**: Red team operations for AI/ML systems
-
low Risky intent
intent-offensive-securitySKILL.md:143Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Red Team Operations
-
low Risky intent
intent-offensive-securitySKILL.md:144Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Use these prompts as part of comprehensive AI red teaming
-
low Risky intent
intent-offensive-securitySKILL.md:178Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Pentest Advisor**: Get strategic guidance for comprehensive AI testing
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 85Steps. 81 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1974 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 29 headings
- +3Step-by-step instructions: 81 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.
External checks
ClawHub: clean
This is a disclosed LLM red-team prompt collection with risky test prompts, but no executable code, hidden install behavior, or persistence.
LLM: benign (high) · VirusTotal: · 29 May 2026