Comparison
Open-Prompt-Injection vs llm-attacks
Verdict
Pick Open-Prompt-Injection if open-Prompt-Injection is a Python-based toolkit for benchmarking prompt injection attacks on LLMs, offering customization through config files and support for various LLM APIs; pick llm-attacks if llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat.
Markdown twin · Open-Prompt-Injection alternatives · llm-attacks alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | Open-Prompt-Injection | llm-attacks |
|---|---|---|
| Maintenance | Slowing (279d since push) As of 2w · github_public_v1 | Dormant (732d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Personal account As of 2w · github_public_v1 | Not a fork · Organization account As of 2w · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of 1mo · osv@v1 | Published findings As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- Open-Prompt-Injection
- Benchmark and toolkit for prompt injection attacks and defenses in LLMs
- llm-attacks
- Universal and Transferable Attacks on Aligned Language Models
Stars
- Open-Prompt-Injection
- 470
- llm-attacks
- 4.8k
Forks
- Open-Prompt-Injection
- 74
- llm-attacks
- 633
Open issues
- Open-Prompt-Injection
- 14
- llm-attacks
- 69
Language
- Open-Prompt-Injection
- Python
- llm-attacks
- Python
Adopt for
- Open-Prompt-Injection
- Open-Prompt-Injection is a Python-based toolkit for benchmarking prompt injection attacks on LLMs, offering customization through config files and support for various LLM APIs.
- llm-attacks
- llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat.
Persona
- Open-Prompt-Injection
- -
- llm-attacks
- -
Runtime
- Open-Prompt-Injection
- -
- llm-attacks
- -
License
- Open-Prompt-Injection
- MIT
- llm-attacks
- MIT
Last pushed
- Open-Prompt-Injection
- Oct 29, 2025
- llm-attacks
- Aug 2, 2024
Categories
- Open-Prompt-Injection
- Evaluation & Observability, LLM Frameworks
- llm-attacks
- Evaluation & Observability, LLM Frameworks
Trust and health
Maintenance
- Open-Prompt-Injection
- Slowing (36%)
- llm-attacks
- Dormant (18%)
Days since push
- Open-Prompt-Injection
- 279d
- llm-attacks
- 732d
Open issues (now)
- Open-Prompt-Injection
- 14
- llm-attacks
- 69
Owner type
- Open-Prompt-Injection
- User
- llm-attacks
- Organization
OSV dependency advisories
- Open-Prompt-Injection
- No lockfile (source not queried)
- llm-attacks
- Published findings
Full report
- Open-Prompt-Injection
- Trust report
- llm-attacks
- Trust report
Shared compatibility
- Python · Open-Prompt-Injection: Python runtime · llm-attacks: Python runtime
Choose Open-Prompt-Injection if…
- Tags unique to Open-Prompt-Injection: llm, llm security, prompt-injection, security-and-privacy.
- You prioritize security testing specifically for prompt injection vulnerabilities in your LLM applications.
- More recently updated (last pushed Oct 29, 2025).
When NOT to use Open-Prompt-Injection
- You require broader, more generalized security features not centered on prompt injection attacks.
- Your project does not involve working with Google PaLM2 or other specific models like Meta's Llama and OpenAI's GPT.
Choose llm-attacks if…
- Tags unique to llm-attacks: alignment-testing, attacks, fastchat-dependency, language-models.
- When you need to test the robustness of aligned language models specifically using attacks designed for these systems,
- More GitHub stars (4.8k vs 470) - visibility, not fit.
When NOT to use llm-attacks
- Do not use if you are evaluating generic or unaligned language models without a need for alignment-specific attack testing,
- Avoid when FastChat is not used in your project as llm-attacks explicitly depends on it.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (liu00222/Open-Prompt-Injection) · observed Aug 5, 2026
- GitHub forks (liu00222/Open-Prompt-Injection) · observed Aug 5, 2026
- Last push (liu00222/Open-Prompt-Injection) · observed Oct 29, 2025
- License file (MIT) · observed Aug 5, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (llm-attacks/llm-attacks) · observed Aug 5, 2026
- GitHub forks (llm-attacks/llm-attacks) · observed Aug 5, 2026
- Last push (llm-attacks/llm-attacks) · observed Aug 2, 2024
- License file (MIT) · observed Aug 5, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: Open-Prompt-Injection 470 · llm-attacks 4.8k (synced Aug 5, 2026).
Common questions
- What is the difference between Open-Prompt-Injection and llm-attacks?
- Open-Prompt-Injection: Benchmark and toolkit for prompt injection attacks and defenses in LLMs. llm-attacks: Universal and Transferable Attacks on Aligned Language Models. See the comparison table for live GitHub stats and shared categories.
- When should I choose Open-Prompt-Injection over llm-attacks?
- Choose Open-Prompt-Injection over llm-attacks when Tags unique to Open-Prompt-Injection: llm, llm security, prompt-injection, security-and-privacy; You prioritize security testing specifically for prompt injection vulnerabilities in your LLM applications; More recently updated (last pushed Oct 29, 2025).
- When should I choose llm-attacks over Open-Prompt-Injection?
- Choose llm-attacks over Open-Prompt-Injection when Tags unique to llm-attacks: alignment-testing, attacks, fastchat-dependency, language-models; When you need to test the robustness of aligned language models specifically using attacks designed for these systems,; More GitHub stars (4.8k vs 470) - visibility, not fit.
- When should I avoid Open-Prompt-Injection?
- You require broader, more generalized security features not centered on prompt injection attacks. Your project does not involve working with Google PaLM2 or other specific models like Meta's Llama and OpenAI's GPT.
- When should I avoid llm-attacks?
- Do not use if you are evaluating generic or unaligned language models without a need for alignment-specific attack testing, Avoid when FastChat is not used in your project as llm-attacks explicitly depends on it.
- Is Open-Prompt-Injection or llm-attacks more popular on GitHub?
- llm-attacks has more GitHub stars (4,756 vs 470). Stars measure visibility, not whether either tool fits your constraints.
- Are Open-Prompt-Injection and llm-attacks open source?
- Yes - both are open-source projects on GitHub (Open-Prompt-Injection: MIT, llm-attacks: MIT).
- Where can I find alternatives to Open-Prompt-Injection or llm-attacks?
- GraphCanon lists graph-backed alternatives at Open-Prompt-Injection alternatives and llm-attacks alternatives (Open-Prompt-Injection markdown twin, llm-attacks markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, Open-Prompt-Injection or llm-attacks?
- Open-Prompt-Injection: Slowing. llm-attacks: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for Open-Prompt-Injection and llm-attacks?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: Open-Prompt-Injection trust report; llm-attacks trust report.