<?xml version="1.0" encoding="utf-8"?><rss version="2.0"><channel><title>Signal Desk: AI</title><link>https://signal-desk-d5t.pages.dev</link><description>Exploited-now security news, threat hunting, AI security and practical playbooks.</description><item><title>Agentic Bug Hunter (community bug-bounty toolkit)</title><link>https://signal-desk-d5t.pages.dev/ai#agentic-bug-hunter</link><guid>https://signal-desk-d5t.pages.dev/ai#agentic-bug-hunter</guid><pubDate>Tue, 13 Oct 2026 00:00:00 +0000</pubDate><category>tool, community</category><description>Built around Claude Code: recon, known-CVE scanning and attack-surface ranking. Caveats: third-party community project, not audited by us; needs Claude Code or API access and won&#x27;t run fully on local models without changes; only point it at targets you&#x27;re authorized to test.</description></item><item><title>GitHub Security Lab Fuzzing Taskflow</title><link>https://signal-desk-d5t.pages.dev/ai#fuzzing-taskflow</link><guid>https://signal-desk-d5t.pages.dev/ai#fuzzing-taskflow</guid><pubDate>Sun, 11 Oct 2026 00:00:00 +0000</pubDate><category>tool</category><description>Open-source taskflows for the seclab-taskflow-agent framework that use an LLM to plan, build and triage fuzzing harnesses. Caveats: needs model API access and real compute; LLM-written harnesses still need human review, and crashes are not vulnerabilities until triaged.</description></item></channel></rss>