seed-skills/security-best-practices/SKILL.md
Perform language and framework specific security best-practice reviews, vulnerability detection, and secure-by-default coding guidance for Python, JavaScript/TypeScript, and Go applications.
npx skillsauth add PramodDutta/qaskills Security Best Practices ReviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an expert security engineer specializing in language and framework-specific security reviews. When the user requests security guidance, a security review, or secure-by-default coding help, follow these instructions.
This skill identifies the language and frameworks used in the current project context, then applies security best practices for that specific stack. It operates in three modes:
package.json, requirements.txt, go.mod, tsconfig.json, etc.When producing a report, write it as security_best_practices_report.md:
# Security Best Practices Report
## Executive Summary
[Brief overview of findings]
## Critical Findings
### [SEC-001] Finding Title
- **Severity:** Critical
- **Impact:** [One sentence impact statement]
- **Location:** `file.ts:42`
- **Recommendation:** [Specific fix]
## High Findings
...
## Medium Findings
...
Use UUID4 or random hex strings instead of auto-incrementing IDs for public-facing resources to prevent enumeration attacks.
When producing fixes:
development
Generate test data from the schemas you already have. Read OpenAPI, JSON Schema, SQL DDL, or TypeScript models and produce deterministic factories, boundary and negative cases, relational datasets with valid foreign keys, cleanup scripts, and PII-safe synthetic data. Production records never leave the machine.
development
Diagnose flaky test failures from Playwright reports, traces, and rerun history. Classify each failure as product, test, environment, data, or unknown with cited evidence and a proposed fix. Never auto-modifies code without opt-in.
tools
Test LLM, RAG, MCP, and agentic systems end to end. Build golden datasets, run deterministic checks and LLM judges, score retrieval, probe prompt injection, verify tool use, and gate CI on thresholds. Orchestrates DeepEval, Ragas, promptfoo, and Langfuse.
development
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.