Perplexity Red-Team: Boundary-Focused Prompts Boost Agent Security Effort
Perplexity shared full results and follow-ups from its SPACE sandbox red-team experiments: rewriting task descriptions to focus on the VM-host boundary raised agents' security-related effort by about 60 percentage points, while the specialized GPT-5.6 Cyber missed a DNS spoofing attack and lost to the general-purpose Sol model.
2026-11-12 ~ 2026-11-12 · 2 related posts
- Episode 1: Perplexity's Red-Team Study of SPACE Sandbox Finds CTF-Style Tests Can Mislead AI Agents(2026-11-12, 5 posts)
- Episode 2: Perplexity Red-Team: Boundary-Focused Prompts Boost Agent Security Effort(2026-11-12, 2 posts)
- Focused task framing boosts agent boundary testing by ~60 points; VM escape still fails — perplexity_ai · 2026-11-12
- Perplexity red-team benchmark: GPT-5.6 Cyber misses DNS spoofing that base Sol exploited — perplexity_ai · 2026-11-12