Open Issues Need Help
View All on GitHub Add a security-model reading order to GETTING_STARTED about 1 hour ago
documentation good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
Cancel superseded CI runs with a concurrency group about 1 hour ago
good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
ScanResult.degraded is never set about 1 hour ago
bug help wanted mentored
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
_fail_closed results carry no stage or latency information about 1 hour ago
good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
Document that scan_output_request ignores request.scanners about 1 hour ago
documentation good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
Duplicate warning blocks in the ML load path about 1 hour ago
good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security
fail_closed config field is read nowhere about 1 hour ago
documentation good first issue
Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.
Python
#ai-safety#llm#prompt-injection#python#sdk#security