Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NovaCode37/claude-security-skills --skill sast-litegit clone --depth 1 https://github.com/NovaCode37/claude-security-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/novacode37/claude-security-skills/sast-lite)<a href="https://agentmods.dev/skills/novacode37/claude-security-skills/sast-lite"><img src="https://agentmods.dev/badge/skills/novacode37/claude-security-skills/sast-lite/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/novacode37/claude-security-skills/sast-lite"><img src="https://agentmods.dev/badge/skills/novacode37/claude-security-skills/sast-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 17 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Tool Misuse · line 36 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.00725 |
| Opus 5 | $0.00041 | $0.00362 |
| Sonnet 5 | $0.00016 | $0.00145 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
sast-lite scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
are actually called — so `subprocess.run(cmd, shell=True)` is flagged while How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAST Lite
An AST-based static analyzer for Python. Instead of fragile regex matching, it
parses each file into an abstract syntax tree and inspects how dangerous APIs
are actually called — so subprocess.run(cmd, shell=True) is flagged while
subprocess.run(["ls"]) is not. No third-party dependencies.
When to use this skill
- "Audit / security-review this Python code."
- "Run a SAST scan on the project."
- Reviewing a PR or untrusted snippet before running it.
- A pre-merge CI gate for security regressions.
What it detects
| Rule | CWE | Severity |
|---|---|---|
eval() / exec() on dynamic input |
CWE-95 | critical/high |
os.system / subprocess(shell=True) |
CWE-78 | high |
pickle/marshal deserialization |
CWE-502 | high |
yaml.load without SafeLoader |
CWE-20 | high |
SQL via f-string / concat / .format / % |
CWE-89 | high |
requests(verify=False) |
CWE-295 | high |
| Hardcoded password/secret literal | CWE-798 | high |
| Weak hash (md5/sha1) | CWE-327 | medium |
tempfile.mktemp |
CWE-377 | medium |
Flask(debug=True) |
CWE-489 | medium |
Jinja2 autoescape=False |
CWE-79 | medium |
assert used for a security check |
CWE-617 | medium |
How to run it
# Scan a directory
python skills/sast-lite/analyzer.py src/
# JSON for tooling / CI
python skills/sast-lite/analyzer.py . --json
# Only show high+ severity
python skills/sast-lite/analyzer.py . --min-severity high
Exit codes: 0 clean · 1 issues found · 2 usage/parse error — ready
for CI gating.
Recommended workflow for Claude
- Run with
--jsonand parse the issue list. - For each issue, open
path:lineand confirm the data flow is genuinely attacker-controllable (the analyzer is intra-procedural, so it may flag patterns that are safe in context). - Propose a concrete fix per finding — e.g. parameterized queries for
py.sql-injection,yaml.safe_loadforpy.yaml-load, list-formsubprocesscalls forpy.subprocess-shell. - Summarize by severity and CWE.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 76 lines · 82 tokens per session scan A 16b6a169a019
sast-lite is a skill published in the GitHub repository NovaCode37/claude-security-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 725 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
owasp-security
Use when reviewing code for security vulnerabilities, implementing authentication/authorization, handling user input, or discussing web application security. Covers OWASP Top 10:2025, ASVS 5.0, LLM Top 10 (2025), and Agentic AI security (2026).
report-writing
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use…
triage-validation
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer…
web2-recon
Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when…
security-arsenal
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/IDOR/path-traversal, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.
web2-vuln-classes
Complete reference for 18 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10…