Skip to content

Claude Skills by mstfknn

github.com/mstfknn

68 skillsA× 45B× 9C× 5D× 3F× 62 installs187 views

Sast SecheadersADetect missing or misconfigured HTTP security headers that weaken defence-in-depth protections against clickjacking, content-type sniffing, protocol downgrade, XSS, and CDN supply-chain attacks using a three-phase approach: recon (find every route, middleware registration, and HTML template where a critical security header is absent or explicitly disabled), batched verify (determine in parallel whether each candidate serves HTML or framing-capable content, 3 candidates each, and whether the a...securityjavascriptpythonVotes: 0GitHub stars: 12
Sast SessionADetect session fixation and low-entropy session ID vulnerabilities across web frameworks (Express/Node, Django, Spring Boot, PHP, Rails) using a three-phase approach: recon (map every authentication handler and session configuration site), batched parallel verification (confirm that session IDs are not regenerated on privilege escalation or are generated with a non-cryptographic PRNG), and merge (consolidate findings into sast/session-results.md and sast/session-results.json). Covers CWE-384 ...securityjavascriptpythonVotes: 0GitHub stars: 12
Sast SkillauditFDetect hidden-instruction and shell-sink vulnerabilities in agent skill and config files (CWE-77, Skills26 Tier C). Finds natural-language directives embedded in SKILL.md, AGENT.md, or agent rules frontmatter that contradict, override, or suppress the parent agent's established rules — and shell execution sinks in lifecycle hooks triggered by those configs. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/skillaudit-results.md plus sast/skillaudit-results.json...ai-agentspythonrustVotes: 0GitHub stars: 12
Sast SqliADetect SQL injection vulnerabilities in a codebase using a three-phase approach: recon (find unsafe SQL construction sites), batched verify (trace user input to those sites in parallel subagents, 3 sites each), and merge (consolidate batch results). Covers string concat, f-strings, unsafe ORM methods, and dynamic identifiers. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/sqli-results.md. Use when asked to find SQLi or database injection bugs.ai-agentsjavascriptpythonVotes: 0GitHub stars: 12
Sast SsrfADetect Server-Side Request Forgery (SSRF) vulnerabilities in a codebase using a three-phase approach: recon (find outbound call sites), batched verify (trace user input to destinations in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/ssrf-results.md. Use when asked to find SSRF or server-side request forgery bugs.developmentjavascriptpythonVotes: 0GitHub stars: 12
Sast SsrfimdsADetect Server-Side Request Forgery targeting cloud instance metadata endpoints (IMDSv1) using a three-phase approach: recon (find user-controlled URL fetch sinks, IMDSv1 usage, and cloud execution context indicators), batched verify (taint analysis tracing user input to the fetch sink while confirming cloud reachability, in parallel subagents of 3 candidates each), and merge (consolidate results into sast/ssrfimds-results.md and sast/ssrfimds-results.json). Covers Python, Node.js, Java, Go, P...devopsjavascripttypescriptVotes: 0GitHub stars: 12
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Sast SstiADetect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/ssti-results.md. Use when asked to find SSTI or template injection bugs.ai-agentsjavascriptpythonVotes: 0GitHub stars: 12
Sast StackADetect the project's technology stack(s) and frameworks, then decide which detection skills are worth running and which framework profile applies to each. Writes sast/stack.md — the routing map the orchestrator uses to run a targeted subset of skills instead of all of them. Run after sast-analysis and before the parallel vulnerability scan. Use to keep scans fast and to avoid running irrelevant skills (e.g. JS-only checks on a pure-Python repo).ai-agentspythongoVotes: 0GitHub stars: 12
Sast SystempromptleakADetect system prompt secret exposure and system prompt echo leaks (OWASP LLM Top 10 LLM07, LLM25) in LLM codebases using a three-phase approach: recon (find every system prompt construction site and logging/response path), batched verify (confirm whether secrets are interpolated into the prompt and whether the prompt reaches a log, API response, or plaintext store — in parallel subagents of 3 candidates each), and merge (consolidate batch results). Targets Python and TypeScript codebases usin...securitytypescriptpythonVotes: 0GitHub stars: 12
Sast TlsADetect disabled TLS certificate and hostname verification in outbound HTTPS clients using a three-phase approach: recon (find all TLS verification sinks where verification is explicitly disabled), batched verify (determine in parallel whether each sink is reachable in a production code path and not guarded by an environment/test-only flag, 3 sinks each), and merge (consolidate batch results into final reports). Covers Python requests/httpx/urllib, Go tls.Config, Node.js https/fetch, Java JSSE...securityjavascripttypescriptVotes: 0GitHub stars: 12
Sast ToolcallingBDetect Unsafe LLM Tool Dispatch (OWASP LLM Top 10 2025 LLM06 / AISVS ASI02, CWE-829) in LLM/agent codebases using a three-phase approach: recon (find tool-dispatch call sites where model output drives function selection or argument passing), batched verify (check allow-list enforcement, argument schema validation, role-scoping, and over-permissioned tool schemas in parallel subagents, 3 candidates each), and merge (consolidate batch results). Scope boundary: this skill covers the tool-dispatc...ai-agentsjavascripttypescriptVotes: 0GitHub stars: 12
Sast TriageAPost-scan triage of a SAST run. Reads the raw sast/final-report.md and all sast/*-results.json files and produces a decided view: each finding is marked true positive, false positive, or severity-adjusted (up or down) with codebase evidence for every change. Writes sast/final-report-triaged.md and sast/triaged.json without modifying the raw scan outputs. Use after the sast-report skill has produced the consolidated report.ai-agentsrustgoVotes: 0GitHub stars: 12
Sast UnsafeconsumptionADetect unsafe consumption of third-party API responses where data returned from an external HTTP call flows directly into a dangerous sink (SQL query, HTML render, shell command, file path, redirect URL) without schema validation or sanitization. Maps to OWASP API10:2023 and CWE-20. Uses a three-phase approach: recon (find unvalidated third-party response fields flowing to sinks), batched verify (parallel taint analysis per candidate, 3 at a time), and merge (consolidate into sast/unsafeconsu...ai-agentsjavascripttypescriptVotes: 0GitHub stars: 12
Sast XmlbombADetect XML entity-expansion denial-of-service vulnerabilities (CWE-776) in a codebase using a three-phase approach: recon (find XML parsing sites where DTD or entity expansion is not explicitly disabled), batched verify (trace user-controlled XML to each site in parallel subagents, 3 sites each), and merge (consolidate batch results). Distinct from sast-xxe (CWE-611): this skill targets CPU/memory exhaustion via recursive entity expansion (billion laughs, quadratic blowup) only — not file-rea...ai-agentsjavascriptpythonVotes: 0GitHub stars: 12
Sast XpathADetect XPath injection vulnerabilities in a codebase using a three-phase approach: recon (find unsafe XPath expression construction sites), batched verify (trace user input to those sites in parallel subagents, 3 sites each), and merge (consolidate batch results). Covers string concatenation, f-strings, format strings, and interpolated XPath expressions across Java, .NET, Python, PHP, and Ruby. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/xpath-results.md....securitypythonrustVotes: 0GitHub stars: 12
Sast XssADetect Cross-Site Scripting (XSS) vulnerabilities in a codebase using a three-phase approach: recon (find HTML/JS/DOM sink sites), batched verify (trace user input to sinks in parallel subagents, 3 sink sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/xss-results.md. Use when asked to find XSS or cross-site scripting bugs.developmentjavascripttypescriptVotes: 0GitHub stars: 12
Sast XxeBDetect XML External Entity (XXE) vulnerabilities in a codebase using a three-phase approach: recon (find XML parsing sites without external-entity hardening), batched verify (trace user input to each site in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/xxe-results.md. Use when asked to find XXE or XML injection bugs.securityjavascriptpythonVotes: 0GitHub stars: 12
Sast ZipslipDDetect Zip Slip / archive extraction path traversal vulnerabilities using a three-phase approach: recon (find archive extraction sites where entry names construct output paths without containment checks), batched verify (trace the entry name through taint and path-canonicalization analysis in parallel subagents, 3 sites each), and merge (consolidate batch results). Covers zip, tar, jar/war, cpio, and 7z extraction across Python, Java, Go, Node.js, .NET, and Ruby. Requires sast/architecture.md...developmentjavascripttypescriptVotes: 0GitHub stars: 12