.claude/skills/review-securityRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Review code changes with Security Review subagent.
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/review-securityRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/review-securityRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/review-securityRuntime, 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 @eohmig/review-securityclawhub inspect @eohmig/review-security --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
sha256:4de40f6de6237203816ffbf3f4ccad02d38b49392889a0a72945613c95cbbdd5skill-card.mdSKILL.mdInitial release of the review-security skill. - Launches a security review subagent to analyze code changes upon `/review-security` command. - Handles checking out the correct branch or PR before review, including stashing with user confirmation if needed. - Formats prompts according to strict requirements and adapts to user instructions (e.g., specific base branch, uncommitted changes). - Handles common failure cases with one retry and user notification if errors persist. - Presents concise summaries and markdown tables of findings, sorted by severity.