Skip to content
Back to search

vulnhound

MarketplaceWorks with Claude CodeGitHub

vulnhound: token-thrifty vulnerability finder for Python projects

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/bu-ra34--vulnhound/badge.svg)](/listings/bu-ra34--vulnhound)

HTML

<a href="/listings/bu-ra34--vulnhound"><img src="/api/listings/bu-ra34--vulnhound/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

As a Claude Code plugin:

/plugin marketplace add bu-ra34/vulnhound
/plugin install vulnhound@vulnhound

The CLI itself (the skill needs it on your PATH):

pip install vulnhound

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines
  1. {
  2. "name": "vulnhound",
  3. "description": "vulnhound: token-thrifty vulnerability finder for Python projects",
  4. "owner": {
  5. "name": "bu-ra34"
  6. },
  7. "plugins": [
  8. {
  9. "name": "vulnhound",
  10. "source": "./",
  11. "description": "Token-thrifty vulnerability finder for Python: finds, proves, fixes without reading the whole repo.",
  12. "version": "0.1.0"
  13. }
  14. ]
  15. }
README.md · README · 67 lines
  1. # vulnhound
  2. **Finds real vulnerabilities. Proves them. Fixes them. Without burning your tokens.**
  3. > Status: pre-alpha. Only `estimate` and `version` work today; the rest is on the roadmap.
  4. [Türkçe](README.tr.md)
  5. ## Why
  6. Asking an LLM to security-review a codebase usually means feeding it the whole repo.
  7. That is expensive, slow, and most of those tokens are code that has nothing to do with
  8. any vulnerability. vulnhound avoids this: cheap static analysis finds candidate flows
  9. first, so the LLM only reads a short list and a few small code slices.
  10. ## How it works
  11. - **The core is the eyes.** A stdlib-only Python program builds an AST index and runs
  12. taint analysis from untrusted sources to dangerous sinks. It never calls an LLM and
  13. prints short JSON.
  14. - **Claude is the brain.** Inside Claude Code, the bundled skill tells Claude to run the
  15. CLI, read only that output plus small slices, judge each finding, write a PoC for the
  16. likely-real ones, prove it in a sandbox, and patch it.
  17. Zero runtime dependencies. Python 3.10+. MIT licensed.
  18. ## Install
  19. As a Claude Code plugin:
  20. ```
  21. /plugin marketplace add bu-ra34/vulnhound
  22. /plugin install vulnhound@vulnhound
  23. ```
  24. The CLI itself (the skill needs it on your PATH):
  25. ```
  26. pip install vulnhound
  27. ```
  28. ## CLI
  29. | Command | What it does |
  30. |---|---|
  31. | `vulnhound analyze [path] [--json] [--no-cache] [--min-severity S]` | Find candidate vulnerabilities. Exit 1 if any. Findings sharing a sink/helper are grouped (`--no-group` to list all); tests/examples/docs dirs and `test_*.py` are skipped unless `--include-tests`; `--include-local-sources` adds local/CLI inputs as sources. |
  32. | `vulnhound slice <id>` | Minimal code slice for one finding. |
  33. | `vulnhound prove <id> --poc FILE [--root DIR] [--backend auto\|docker\|unshare] [--timeout S] [--json] [--verbose]` | Run a PoC in a sandbox (no network, resource-limited). Prints PROVEN (exit 0), SAFE (1) or UNVERIFIED (3). |
  34. | `vulnhound estimate [path] [--json]` | Rough token cost (bytes/4) of reading the whole repo. |
  35. | `vulnhound report [--format json\|sarif\|markdown] [-o FILE]` | Render findings. |
  36. | `vulnhound version` | Print version. |
  37. Exit codes: 0 ok / no findings, 1 findings found, 2 usage error (e.g. unknown id), 3 UNVERIFIED (prove).
  38. ## Proving a finding
  39. `vulnhound prove <id> --poc poc.py` runs a small standalone Python PoC in a sandbox (network off, memory/CPU/time limited, project mounted read-only) and reports a verdict. The PoC triggers the vulnerable code with a malicious input and calls `proven("detail")` from `vulnhound.poc` when the exploit works, or `safe("detail")` when it is blocked. `canary_path()` returns a secret file outside the project, for path-traversal PoCs to read. No marker and exit 0 means SAFE; sandbox missing, timeout or a crashing PoC means UNVERIFIED. The PoC never runs on the host.
  40. Caveat: the sandbox needs docker or unshare. The PoC runs against your project, so third-party imports must be importable inside it: the `unshare` backend sees the host venv read-only, while the `docker` backend uses a clean python image, so PoCs needing framework imports may report UNVERIFIED there. Pick `--backend unshare` when the PoC imports your installed deps.
  41. ## Security
  42. Scan only code you own. See [SECURITY.md](SECURITY.md).
  43. ## License
  44. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.