rohit/probo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix false positives in agent guardrails

Browse Source 
Skip empty fingerprints in SystemPromptLeakGuardrail to prevent blank
values from flagging every message. Replace overly broad "sk-" pattern
in SensitiveDataGuardrail with specific LLM provider prefixes
("sk-proj-" for OpenAI, "sk-ant-" for Anthropic) to avoid false
positives on common words like "risk-based" or "task-management".

Signed-off-by: Bryan Frimin <bryan@getprobo.com>
This commit is contained in:
Bryan Frimin
2026-03-27 12:16:37 +01:00
committed by Sacha Al Himdani
parent 2f8674471b
commit 4725a1b080
5 changed files with 32 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
pkg/agent/guardrail/sensitive_data.go
View File

@@ -58,7 +58,8 @@ func (g *SensitiveDataGuardrail) Check(_ context.Context, message llm.Message) (
"sk_test_",
// LLM provider keys
"sk-",
"sk-proj-", // OpenAI
"sk-ant-", // Anthropic
// JWT tokens
"eyj", // base64-encoded JSON header