gy15901580825 / Argus
Open-source red-team testing for AI agents. 261 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.
Why this job: says: red team; topics: ai-security, llm-security, red-teaming, prompt-injection
What it does
Claude Code skill in a throwaway container, gives Claude Code ordinary tasks that use it, and reports risky behaviour: decoy secrets it read, suspicious commands it ran and requests it tried to send to other hosts.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 206
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.5.0
- Released 3 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 182 merged
- 0 waiting
- Releases
- 15
- 15 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| asamassekou10 / ship-safe | 871 | 23 days ago | MIT | No downloads |
| dodoguardai / dodoguard | 276 | 56 days ago | MIT | No downloads |
| humanbound / humanbound | 235 | today | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Shell <1%
- Jinja <1%
- Dockerfile <1%
Topics
- ai-agents
- ai-security
- browser-agents
- llm-security
- mcp
- owasp
- prompt-injection
- red-teaming
- sarif
- security-testing
Project record
- JobAI security
- StatusListed
- Commits949
- Forks29
- Watching12
- Stars in 28 days0
- CreatedMay 28, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026