Muhammad Basit Ali
@basitalisandhu
Cloud security, AI agent security and the tooling around them: AWS guardrails, Microsoft 365 governance, MCP servers, Claude Code skills.
24
Published Tools
6
Total Stars
0
Weekly Downloads
8
GitHub Followers
94
Public Repos
98/100
Avg Security
Published Tools
20 MCP Servers3 Skills1 Agentacross 3 categoriesbasitalisandhu
Claude Code skills, every skill I maintain in one repository: 87 skills in 13 plugins for AWS and Microsoft 365 security, agent security, compliance evidence, repository engineering, debugging, DevOps, docs and data, vendored from their source packs and synced daily. One marketplace add, or one clone and one install command. Offline, no telemetry.
...morebasitalisandhu
Parse, explain and validate 5-field cron expressions and list upcoming runs in a time zone.
basitalisandhu
Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, user input in system prompts, over-broad tools, MCP servers without auth, leaked keys and unsafe model loading. 36 tested rules, CWE and OWASP mapping.
...morebasitalisandhu
Claude Code skills for repository audits and documentation: verify README and docs claims against the code, run audits where every finding cites a resolvable path:line, write AGENTS.md and CLAUDE.md with only what code cannot say, check a README's first screen, rank test gaps. Tested standard-library scripts, no network.
...morebasitalisandhu
Claude Code skills for ways of working, from files already on disk: change requests from a Terraform plan or PR export, an action ledger across meeting notes, a security exception register, RFC lifecycle lint, a decision log, weekly status notes, a private 1:1 ledger, focus time from a calendar export, a risk register refresh. Offline.
...moreLint Dockerfiles for root users, latest tags, secrets in ENV or ARG, missing HEALTHCHECK and more.
Read-only git statistics for a local repository: log, blame ownership, churn, authors, large files.
Validate JSON against a schema with Ajv, infer a schema from samples and diff two schemas.
Decode JWTs without verifying, flag risky algorithms and claims, verify HS256 or RS256 with a key.
Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.
Lint OpenAPI 3.x documents for missing security, responses, descriptions and versioning.
Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.
Test regular expressions in a timeout-guarded worker, explain them, find catastrophic backtracking.
Fetch a URL's response headers and grade CSP, HSTS, X-Frame-Options and related security headers.
Parse, explain and validate 5-field cron expressions and list upcoming runs in a time zone.
Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG, missing HEALTHCHECK and more.
Read-only git statistics for a local repository: log, blame ownership, churn, authors, large files.
Validate JSON against a schema with Ajv, infer a schema from samples and diff two schemas.
Decode JWTs without verifying, flag risky algorithms and claims, verify HS256 or RS256 with a key.
Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.
Lint OpenAPI 3.x documents for missing security, responses, descriptions and versioning.
Query OSV.dev for known vulnerabilities by package and version, and scan lockfiles in batch.
Test regular expressions in a timeout-guarded worker, explain them, find catastrophic backtracking.
Fetch a URL's response headers and grade CSP, HSTS, X-Frame-Options and related security headers.