.claude/skills/jarvis-voiceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/jarvis-voiceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/jarvis-voiceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/jarvis-voiceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @globalcaos/jarvis-voiceclawhub inspect @globalcaos/jarvis-voice --version 3.2.1This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:aebcd24aabe37ab1442765f42dbb66fbd6c8e05201fe7628aa273a9363604d64_meta.jsonbin/jarvisskill-card.mdSKILL.mdtemplates/HUMOR.mdtemplates/SESSION.mdtemplates/VOICE.mdHardening pass on the 3.2.0 audit findings. bin/jarvis now creates temp files with mktemp in a private 0700 dir (predictable $$ names allowed a same-user overwrite). Speaking is explicitly opt-in and no longer triggers merely because the last message contained audio. Translating or summarising into English for speech now requires the user's consent instead of happening silently. The personality templates lead with per-session use; workspace-wide install is a deliberate per-file choice with precedence rules and an uninstall command.