Whistleblower
Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily
Whistleblower scores 2.8/10 (Nascent) in Guardrails & Security.
Language Python License No license (all rights reserved) Stars 157★ Type lightweight Self-host Yes Repo Repello-AI/whistleblower Homepage https://github.com/Repello-AI/whistleblower
Quality
Nascent 2.8
Adoption 5
Activity 5
Maturity 72
Community 12
Capability 50
Show the math
Overall 2.8/10
value = 2.8/10
score = value
Adoption 1.4/10
value = 5/100
score = 1 + 9 * value / 100
Activity 1.4/10
value = 5/100
score = 1 + 9 * value / 100
Maturity 7.5/10
value = 71.7/100
score = 1 + 9 * value / 100
Community 2.1/10
value = 11.9/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
157★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
2y Project age
8mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- No license
No OSS license
No recognized open-source license is declared; using it commercially is legally ambiguous.
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
prompt-leakage red-team reconnaissance api testing