Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
2 results with any of your words
Clear search and filters
-
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
-
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.