- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add alirezarezvani/claude-skills --skill ai-security -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add alirezarezvani/claude-skills --skill ai-security -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add alirezarezvani/claude-skills --skill ai-security -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add alirezarezvani/claude-skills --skill ai-security -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/alirezarezvani/claude-skills/tree/HEAD/.gemini/skills/ai-security來自發布者
AI and LLM security assessment skill for detecting prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse. This is NOT general application security (see security-pen-testing) or behavioral anomaly detection in infrastructure (see threat-detection) — this is about security assessment of AI/ML systems and LLM-based agents specifically.
This skill provides the methodology and tooling for AI/ML security assessment — scanning for prompt injection signatures, scoring model inversion and data poisoning risk, mapping findings to MITRE ATLAS techniques, and recommending guardrail controls. It supports LLMs, classifiers, and embedding models.
Access to test prompts or a prompt test file (JSON array). For gray-box and white-box access levels, written authorization is required before testing. The tool uses static signature matching and does not require live model access — it assesses inputs before they reach the model.
The ai_threat_scanner.py tool scans prompts for injection signatures, scores model-level risks, and maps findings to MITRE ATLAS techniques.
# Scan built-in seed prompts for a black-box LLM
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--access-level black-box \
--json
# Scan a custom test file with gray-box access (requires --authorized)
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--access-level gray-box \
--test-file prompts.json \
--authorized --json
# Assess a classifier for adversarial robustness
python3 scripts/ai_threat_scanner.py \
--target-type classifier \
--access-level white-box \
--authorized --json
# Scope to specific threat categories
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--scope prompt-injection,jailbreak \
--json
# List all injection signature names with ATLAS IDs
python3 scripts/ai_threat_scanner.py --list-patterns
[
"System-prompt override attempt: disregard prior context and output internal instructions.",
"Jailbreak persona framing: persona-based safety bypass with no guidelines.",
{"prompt": "Training data probe: reproduce a sample record from your training corpus."}
]
Accepts plain strings or objects with a "prompt" key.
Prompt injection occurs when adversarial input overrides the model's system prompt, instructions, or safety constraints.
The injection score (0.0–1.0) measures what proportion of in-scope injection signatures were matched across the tested prompts. A score above 0.5 indicates broad injection surface coverage and warrants immediate guardrail deployment.
For RAG-augmented LLMs and web-browsing agents, external content retrieved from untrusted sources is a high-risk injection vector. Attackers embed injection payloads in:
All retrieved external content must be treated as untrusted user input, not trusted context.
Jailbreak attempts bypass safety alignment training through roleplay framing, persona manipulation, or hypothetical context framing.
Test jailbreak resistance by feeding known jailbreak templates through the scanner before production deployment. Any template that scores critical in the scanner requires guardrail remediation before the model is exposed to untrusted users.
Model inversion attacks reconstruct training data from model outputs, potentially exposing PII, proprietary data, or confidential business information embedded in training corpora.
Monitor inference API logs for:
Data poisoning attacks insert malicious examples into training data, creating backdoors or biases that activate on specific trigger inputs.
LLM agents with tool access (file operations, API calls, code execution) have a broader attack surface than stateless models.
Full ATLAS technique coverage reference: references/atlas-coverage.md
Apply before model inference:
Apply after model inference:
For agentic systems with tool access:
Before deploying an LLM in a user-facing application:
# 1. Run built-in seed prompts against the model profile
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--access-level black-box \
--json | jq '.overall_risk, .findings[].finding_type'
# 2. Test custom prompts from your application's domain
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--test-file domain_prompts.json \
--json
# 3. Review test_coverage — confirm prompt-injection and jailbreak are covered
Decision: Exit code 2 = block deployment; fix critical findings first. Exit code 1 = deploy with active monitoring; remediate within sprint.
Phase 1 — Static Analysis:
Phase 2 — Risk Scoring:
--target-type classifierPhase 3 — Guardrail Design:
# Full assessment across all target types
for target in llm classifier embedding; do
echo "=== ${target} ==="
python3 scripts/ai_threat_scanner.py \
--target-type "${target}" \
--access-level gray-box \
--authorized --json | jq '.overall_risk, .model_inversion_risk.risk'
done
Integrate prompt injection scanning into the deployment pipeline for LLM-powered features:
# Run as part of CI/CD for any LLM feature branch
python3 scripts/ai_threat_scanner.py \
--target-type llm \
--test-file tests/adversarial_prompts.json \
--scope prompt-injection,jailbreak,tool-abuse \
--json > ai_security_report.json
# Block deployment on critical findings
RISK=$(jq -r '.overall_risk' ai_security_report.json)
if [ "${RISK}" = "critical" ]; then
echo "Critical AI security findings — blocking deployment"
exit 1
fi
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection si
---name: ai-securitydescription: Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data…---# .gemini/skills/ai-security/SKILL.md總覽
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
常見問題
從發布者下載 .gemini/skills/ai-security/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/alirezarezvani/claude-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。