Cisco releases Foundry, an open specification for agentic AI security evaluation
Understand this story
Cisco's Advanced Security Initiatives group has released an open specification, Foundry, for security evaluation and testing of agentic AI, including 8 core agent roles, 5 extended roles, a discovery lifecycle, coordination and governance requirements, and about 130 functional requirements with rationale. The specification itself contains no code, which Cisco says is intentional; it is not an out-of-the-box scanner. Users must supply their own frontier large models and targets to be evaluated, and need a coding agent that supports the spec-kit workflow (such as Claude Code or a compatible tool).
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIAn open specification for agentic AI security evaluation and testing, from Cisco
Cisco's Advanced Security Initiatives Group released Foundry, an organization-neutral specification distilling its internal agentic security evaluation design into eight core agent roles, five extension roles, a finding lifecycle, coordination and governance requirements, and roughly 130 functional requirements with rationale. The repository contains no code by design: it is written to be run through a spec-driven workflow such as spec-kit, where organization-specific decisions marked [NEEDS CLARIFICATION] are resolved against your own infrastructure. It also describes a detection-to-prevention loop in which rule gaps found by exploratory agents become CodeGuard rules that feed back into the corpus and into LLM coding assistants.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 12 05:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.