whistleblower
A security testing tool for AI applications to uncover prompt leakage and capability flaws via API interactions.
GraphCanon updated Oct 6, 2026 · GitHub synced Oct 6, 2026
30views this month
Decision brief
Whistleblower is an offensive security tool for AI applications to detect prompt leakage and capability flaws via malicious API probing.
Good fit when
- When performing ethical hacking on LLM-based apps for security testing
- For discovering system weaknesses in AI apps exposed through APIs
Avoid when
- If the focus is on non-API interaction based security vulnerabilities
- When working with proprietary or restricted AI models that prohibit external probing
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (339d since push)
- As of Oct 6, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 6, 2026
- Security (OSV)
- 10 low (10 low)
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install whistleblowerSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Whistleblower aids in detecting vulnerabilities within LLM-based applications by probing system weaknesses through the use of malicious prompts and injections, designed for ethical hacking purposes.
Capability facts
- Languages
- python
Source: github.language · Oct 6, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Oct 6, 2026)
pip install -r requirements.txtSource link
Tags
README
Requirements The required packages are contained in the file. You can install the required packages using the following command:
For agents
This page has a .md twin and JSON over the API.