INTEL_REPORT
Trail of Bits — Security engineering · published 2/20/2026, 4:00:00 PM · TLP amber
Summary
Ingested excerpt (first ~500 chars of normalized text).
Using threat modeling and prompt injection to audit Comet Before launching their Comet browser, Perplexity hired us to test the security of their AI-powered browsing features. Using adversarial testing guided by our TRAIL threat model, we demonstrated how four prompt injection techniques could extract users’ private information from Gmail by exploiting the browser’s AI assistant. The vulnerabilities we found reflect how AI agents behave when external content isn’…
https://blog.trailofbits.com/2026/02/20/using-threat-modeling-and-prompt-injection-to-audit-comet
sha256:40e1480731bc8dc5e26b4381124bf9a53b3f7688ebbd79e593b84c45c89e0a63
What we pulled out
Deterministic extractor (IOC + allowlisted tokens + ATT&CK IDs present in DB).
Indicators
Linked with report → mentions → indicator. Values open the indicator workspace.
Malware families
Allowlist token matches only.
Threat actors mentioned
Allowlist mentions — not a formal attribution verdict.
ATT&CK techniques
MITRE IDs referenced in text and present in local technique table.
CONTINUE INVESTIGATION
High-signal pivots without leaving the thread you started in search.
Browse the report corpus.
Neighborhood from the first linked indicator.