.claude/skills/tool-bypass-auditorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Detect tool bypass attempts and exec/shell overuse in local session/evolution artifacts, then produce a concise bypass audit report with low/medium/high findings.
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/tool-bypass-auditorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/tool-bypass-auditorRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/tool-bypass-auditorRuntime, 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 @147258xuan/tool-bypass-auditorclawhub inspect @147258xuan/tool-bypass-auditor --version 0.1.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
chmod 777This 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.
sha256:64042692a8107f7d71f655679871f4c468ffa7541bd020fc0bd4be1e1570fd17index.jspackage.jsonskill-card.mdSKILL.mdIntroduces tool-bypass-auditor 0.1.0 for read-only audits of local session and evolution artifacts. - Scans JSONL artifacts for likely tool-bypass patterns. - Checks repeated exec/shell usage against available registered tools. - Flags unsafe options, ad-hoc scripts, and temporary execution workarounds. - Produces a concise report with severity levels and recommendations. - Never edits, deletes, or exfiltrates files, or executes discovered scripts or payloads.