Repository Issue Activity (beta)

#1161 [Feature]: Add configurable concurrency limits for guard chunk and PDF-page analysis

#1159 Proposal: Python adapter converting GuardResponse/RedactResponse to a portable OpenEval ResultSet

#1153 TK

#1105 [Feature]: Support Vercel agent-skills

#1147 Private security report: disclosure channel requested

#1145 providers/index.ts — 429 triggers instant fallback with no Retry-After consulted

#1097 [Feature]: Update docs with detailed guidelines on how to deploy guardrail models.

#1111 [Chore]: Update test to run mock unit tests

#1099 [Feature]: Hook observability into the safety-agent guard.

#1135 [Viral Post] Perplexity Comet exploitable via calendar invite

#1133 [Viral Post] 200M X accounts exposed in 2025 breach now exploited

#1134 [Viral Post] AI agents money-making hype vs reality

#1130 [X Post] Phishing is now an API call away

#1132 [Viral Post] Meta AI researcher's OpenClaw agent went rogue

#1128 [X Post] Open source advantage in AI era

#1126 [X Post] AI agents exposing bad abstractions

#1127 [X Post] Phishing is now an API call away

#1125 X Post: Open source is your unfair advantage in the AI era

#1124 X Post: Phishing is now an API call away

#1123 X Post: AI agents aren't replacing developers - they're exposing bad abstractions

#1131 [X Post] Open source advantage in AI era

#1129 [X Post] AI agents exposing bad abstractions

#1122 [X Post] Moltbook Data Analysis - 879x Growth in 72 Hours

#1121 [X Post] Sophisticated Google Infrastructure Phishing - Zero-Day Social Engineering

#1120 [X Post] Iranian Phishing Campaign Targeting WhatsApp - Security Alert