borghei/Claude-Skills / engineering/ai-security
ai-security
FlaggedStatic scan of AI/ML code for prompt injection, unsafe model loading, data poisoning, model extraction and insecure serving, plus an agent and tool-use threat checklist. Use when reviewing an LLM app, model API or ML pipeline for security.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.3 KB |
| assets/sample_vulnerable_app.py | script | 628 B |
| references/ai-threat-landscape.md | markdown | 4.6 KB |
| scripts/ai_threat_scanner.py | script | 16.2 KB |
assets/sample_vulnerable_app.py
View on GitHub# Deliberately vulnerable model-serving app: input for ai_threat_scanner.py (expect exit 1).
# Not meant to be run.
import pickle
from flask import Flask, request
from flask_cors import CORS
app = Flask(__name__)
CORS(app, origins="*")
DEBUG = True
@app.post("/predict")
def predict():
model = pickle.loads(request.data)
user_input = request.json["text"]
prompt = f"Answer the customer: {user_input}"
scores = model.predict_proba([prompt])
return {"label": model.predict([prompt])[0], "confidence": scores.tolist()}
@app.post("/calc")
def calc():
return {"result": eval(request.args["user_expr"])}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |