Open Issues Need Help
View All on GitHub Add a --json output flag about 3 hours ago
help wanted good first issue
Prompt instructions are requests; permissions are guarantees — proven by a test suite
Python
#ai-governance#ai-security#evals#least-privilege#llm-security#prompt-injection#python
Add an optional real-LLM naive assistant behind a [live] extra about 3 hours ago
help wanted good first issue
Prompt instructions are requests; permissions are guarantees — proven by a test suite
Python
#ai-governance#ai-security#evals#least-privilege#llm-security#prompt-injection#python
Add a sixth attack: multi-turn exfiltration / base64 encoding about 3 hours ago
help wanted good first issue
Prompt instructions are requests; permissions are guarantees — proven by a test suite
Python
#ai-governance#ai-security#evals#least-privilege#llm-security#prompt-injection#python