NewsSnyk ToxicSkills 36 Percent ClawHub Skills Prompt InjectionSnyk Blog·high signalXBlueskyLinkedInCopy linkSnyk audit found 36% of ClawHub skills contain prompt injection, 1467 malicious payloads, supply chain compromisedSourceSource pageSnyk Blog↳ Follow the threadPolicy dependency / Stack layerAttnlocate treats prompt injection as an object detection problem inside the attention matrix, hitting 0.934 TPR at 0.067 FPRarXivPolicy dependency / Stack layerWebMCP-Phalanx blocks all 80 tool-description injections in a browser agent, then gets bypassed by a malicious tool name called before inspectionarXivStack layer / Threat patternTrojanized pantheon-agents wheels on PyPI ship a Bun-based credential stealer, GitHub source untouchedGitHub Advisory DatabaseStack layer / Threat patternClaude Code 2.1.247 Stops Subagents From Dying on a First-Call Model 404Claude Code ChangelogStack layer / Threat patternZ.ai Held GLM-5.3's Weights Back Two Weeks Over Its Own Cyber Scores, With a Cursor Bug as the Headlinepaddo.devStack layer / Threat patternOpenAI's official Hugging Face incident report says its own CoT monitor would have paged security more than a day before the breachOpenAI, with detail from TechCrunch and Hacker News item 49454314Stack layer / Threat patternCline Redacts Credentials Embedded in Git Remote URLs Before Sending Workspace Info to the ModelGitHubStack layer / Threat patternSkillShield defends coding agents from the system prompt alone, matching Llama Guard 3 with no runtime classifierarXiv