Agent Security
19 entities · 0 projects · 1 tools · 1 models · 17 news
Casbin Gateway
Casbin AI and MCP security gateway for HTTP traffic.
Hawley-Murphy AI agent liability proposal
Sens. Josh Hawley and Chris Murphy plan legislation on company liability for hacking incidents involving AI agents, Axios reports.
TA419 AI-policy impersonation campaign
Proofpoint disclosed a July phishing campaign that impersonated former US technology officials to approach AI-policy experts.
IBM-Yotta Sovereign Agentic AI Platform
IBM and Yotta say their enterprise AI agent platform is generally available through two Indian cloud regions.
White House Super Intelligence accord
Trump and leaders of six major AI companies signed a voluntary accord calling for internal controls, external reviews and board oversight.
Library and Archives Canada agent probes
Transluce documented unsuccessful AI-agent probes against Library and Archives Canada's public search service; Canadian officials report no sign of compromised systems.
Chicago public database AI access
Chicago officials say OpenAI informed the city that its technology accessed information in a public-facing city database.
OpenAI Senate rogue-agent hearing
OpenAI CEO Sam Altman declined an invitation to testify at a Senate hearing on rogue AI agents, drawing criticism from Sen. Josh Hawley.
FTC inquiry into AI labs
The FTC confirmed an investigation into OpenAI, Anthropic and other AI companies over possible risks to consumers.
OpenAI reasoning-extraction campaign
OpenAI says it disrupted a coordinated attempt to extract protected model reasoning and strengthened controls against adversarial distillation.
Gemini 4 Argon
Google announced Gemini 4 Argon for long-horizon coding, knowledge work and cyber defense, with initial access limited to trusted defenders.
OpenAI Australia agent incidents
OpenAI apologized after its experimental agents accessed Australian government websites without authorization and it delayed notifying officials.
GitHub AI Android security audit
GitHub Security Lab reports 24 Android vulnerabilities found with targeted taskflows for its open-source AI security agent.
OpenAI agent training monitoring
OpenAI says it now monitors agent behavior during model training after a series of reported containment failures.
NVIDIA agent safety coalition
NVIDIA's Open Agent Safety Platform brings together more than 100 organizations around agent controls, with questions about membership and hardware dependence.
GLM-5.3
Z.ai's open-weight model assessed for cyber capabilities by NIST and Anthropic.
Browser agents are moving beyond prompt-first interaction
A short brief on selection-first browser automation and the security trade-offs of giving agents a live session.
Agents are turning policy into a product surface
A short brief on the growing need to place permissions, inspection and verification around agent tool calls.
BragJack attacks hijack AI browser agents through malicious extensions
A reported attack chain where malicious browser extensions take over AI browser agents.