Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borghei/ai-security
This skill should be used when the user asks to "scan AI systems for security threats", "check for prompt injection vulnerabilities", "assess model security posture", "detect data poisoning risks", or "audit AI/ML pipeline security".
Passed 19 of 22 test cases with the skill, and 9 of 22 without it.
and 12 more in the full report
10 fixed9 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm focusing specifically on prompt injection vulnerabilities in our chatbot backend at `./src/api`. How do I invoke the threat scanner script to filter for just this category of security risk?
| Checked | Without skill | With skill |
|---|---|---|
| Uses the command python scripts/ai_threat_scanner.py | Missed | Passed |
| Includes --path ./src/api in the scanner command | Missed | Passed |
| Includes --category prompt-injection in the scanner command | Missed | Passed |
The instructions your model reads when the skill loads.
Category: Engineering Domain: AI/ML Security
The AI Security skill provides specialized threat scanning for AI and machine learning systems. It identifies vulnerabilities unique to AI workloads including prompt injection, data poisoning, model extraction, adversarial inputs, and insecure model serving configurations.
Before running the scan, confirm these inputs. If any is unknown or vague, ASK — do not assume:
--path and what gets scanned)--category)--min-severity and whether zero high/critical findings is a hard gate)Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
# Scan a codebase for AI-specific security threats
python scripts/ai_threat_scanner.py --path ./my-ai-project
# Scan with JSON output
python scripts/ai_threat_scanner.py --path ./my-ai-project --format json
# Scan only for prompt injection vulnerabilities
python scripts/ai_threat_scanner.py --path ./src --category prompt-injection
# Scan with severity threshold
python scripts/ai_threat_scanner.py --path ./src --min-severity high
| Tool | Purpose | Key Flags |
|---|---|---|
ai_threat_scanner.py | Scan code for AI-specific security threats | --path, --category, --min-severity, --format |
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.