Skip to content

Conversation

@moscowchill
Copy link

  • Add OpenRouter as third LLM provider option alongside Ollama and Groq
  • Add _openrouter_request() method for OpenRouter API calls
  • Support automatic API key loading from .env file (openrouterkey or OPENROUTER_API_KEY)
  • Default model: anthropic/claude-sonnet-4
  • Update README with OpenRouter documentation and examples

🤖 Generated with Claude Code

moscowchill and others added 2 commits November 25, 2025 13:18
- Add OpenRouter as third LLM provider option alongside Ollama and Groq
- Add _openrouter_request() method for OpenRouter API calls
- Support automatic API key loading from .env file (openrouterkey or OPENROUTER_API_KEY)
- Default model: anthropic/claude-sonnet-4
- Update README with OpenRouter documentation and examples

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>
- Add --retries as alias for --selector-retry
- Show default values in help text for --threads and --selector-retry
- Update CLI examples to include OpenRouter usage

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>
@moscowchill
Copy link
Author

I thought the whole point of this tool was an added default/weak password generator per page?
But you chose for having the user specify a list?

- LLM now identifies vendor/product during analyze phase (HP, Cisco, etc.)
- New --default-creds flag filters 3,600+ credentials by detected vendor
- Stores detected_vendor and detected_product in database
- Add load_default_creds() and get_detected_vendor() utility functions
- Bundle DefaultCreds-Cheat-Sheet.csv with repo
- Make --usernames/--passwords optional when using --default-creds
- Update README with default credentials workflow examples

Usage:
  python BruteForceAI.py analyze --urls targets.txt --llm-provider openrouter
  python BruteForceAI.py attack --urls targets.txt --default-creds

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>
@moscowchill
Copy link
Author

Feature Complete: Default Credentials with LLM Vendor Detection

What was added:

  1. Vendor Detection - During analyze, the LLM now identifies the vendor/product (e.g., "HP / Aruba Instant On 1930 Switch")
  2. --default-creds Flag - New attack option that:
    - Looks up detected vendor from database
    - Filters the 3,681 default credentials to only matching vendors
    - Uses those credentials automatically
  3. Bundled CSV - DefaultCreds-Cheat-Sheet.csv is now included in the repo

Tested on your switch:
🔍 https://10.10.10.7:4343/: Detected vendor 'HP', filtering credentials...
Found 19 matching credentials
📋 Total unique credentials: 19 (9 usernames, 15 passwords)

Usage:

Step 1: Analyze (detects vendor)

python BruteForceAI.py analyze --urls targets.txt --llm-provider openrouter

Step 2: Attack with filtered default creds

python BruteForceAI.py attack --urls targets.txt --default-creds

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant