Listenly

Can organizations reduce vulnerability whack-a-mole cycles by using memory-safe languages and trusted software repositories?

Answered at 24:02 in The Agents Ran All Weekend. They Came Back With Zero Days. ft. Omar Santos, Distinguished Engineer, AI Security @ Cisco · Security & GRC Decoded

— questions searchable right now

Can organizations reduce vulnerability whack-a-mole cycles by using memory-safe languages and trusted software repositories?

Yes. Organizations should eliminate structural risk by using vetted, lightweight base images like Chainguard or Socket that remove 75% of unnecessary components. They should also establish trusted repositories so AI agents pick approved libraries instead of random internet sources. Additionally, migrating high-vulnerability code to memory-safe languages—for example, moving from C++ implementations with thousands of findings to safer alternatives—reduces ongoing vulnerability discovery and fixes.

Omar Santos on Security & GRC DecodedAll answers from this podcast →
Full answer and detailsRead the whole answer, key facts and every other question from this episode

In short

Yes.

Omar Santos, Distinguished Engineer, AI Security at Cisco · The Agents Ran All Weekend. They Came Back With Zero Days. ft. Omar Santos, Distinguished Engineer, AI Security @ Cisco · Security & GRC Decoded · answer at 24:02

Quote to remember

“The agents ran all weekend. They came back with zero days: the exploit, the mitigation, even compensating controls, the fix, the unit tests, the regression tests, and documentation.”

— Omar Santos

The full answer · about 3 min

Yes. Organizations should eliminate structural risk by using vetted, lightweight base images like Chainguard or Socket that remove 75% of unnecessary components. They should also establish trusted repositories so AI agents pick approved libraries instead of random internet sources. Additionally, migrating high-vulnerability code to memory-safe languages—for example, moving from C++ implementations with thousands of findings to safer alternatives—reduces ongoing vulnerability discovery and fixes.

Key facts

  • 400,000 repositories: scale at which Cisco is attempting to find vulnerabilities and simulate attacks
  • 75% of unnecessary components: proportion eliminated from lightweight base images like Chainguard or Socket
  • Milliseconds to seconds: time frame in which agent drift can occur in non-deterministic agentic environments

People, companies and topics mentioned

CiscoAnthropicOpenAIGoogleModel Context Protocol (MCP)ChainguardSocketOpenSSL

More answers from this episode

 ·  All answers from Security & GRC Decoded →
—
—
0:00
0:00