Damn Vulnerable LLM Agent logo

Damn Vulnerable LLM Agent

Guardrails & Security 3.1/10 Emerging

Intentionally insecure ReAct agent for learning and demonstrating prompt-injection and tool-abuse attacks against agentic apps.

Damn Vulnerable LLM Agent scores 3.1/10 (Emerging) in Guardrails & Security.

Language Python License Apache-2.0 Stars 483★ Type lightweight Self-host Yes Repo ReversecLabs/damn-vulnerable-llm-agent Homepage https://github.com/ReversecLabs/damn-vulnerable-llm-agent

Quality

Emerging 3.1
Adoption 17
Activity 2
Maturity 60
Community 33
Capability 50
Show the math
Overall 3.1/10
value = 3.1/10
score = value
Adoption 2.5/10
value = 17.1/100
score = 1 + 9 * value / 100
Activity 1.1/10
value = 1.6/100
score = 1 + 9 * value / 100
Maturity 6.4/10
value = 59.5/100
score = 1 + 9 * value / 100
Community 4/10
value = 33.3/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100

Key metrics

483★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
2.6y Project age
1y ago Last commit

Gotchas

No gotchas documented yet. Contribute one if you know a constraint we missed.

Labels

  • Inactive

    No push in 1y

    No commits in over a year; effectively dormant.

  • Self-hosted

    Self-hosted

    You deploy and operate it yourself; there is no hosted option here.

training prompt-injection react-agent education red-team