Identify security risks in AI skills before installation.
npx skills add https://github.com/joneqian/EvoClaw --skill skill-vetter-joneqian
Please help me install this Agent Skill. Skill: skill-vetter Source: https://github.com/joneqian/EvoClaw/tree/main/packages/core/src/skill/bundled/skill-vetter Command: npx skills add https://github.com/joneqian/EvoClaw --skill skill-vetter-joneqian
This Skill automates security vetting before installing AI skills by identifying red flags, analyzing permission scopes, and evaluating trust signals to prevent unsafe integrations.
Provide the target skill's SKILL.md and related files to initiate the vetting workflow and generate a safety report.
High-intent search queries and answers about installing and using this skill.
To vet AI skills for security risks, provide the target skill's SKILL.md and related files to trigger an automated workflow that checks source origin, mandates code review, and evaluates permission scopes to produce a structured safety report.
During an AI skill code review, identify high-risk patterns and insecure practices by examining all skill files, evaluating network access requirements, and analyzing permission scopes to detect potentially malicious or unsafe integrations.
You can evaluate trust signals for AI skills from GitHub, ClawdHub, or other sources by checking the author reputation, origin, and community signals to assess overall trustworthiness before integration.
The best way to classify risk levels for unsafe AI skill integrations is to enforce a four-step vetting workflow that assigns a low, medium, or high risk level and provides actionable remediation guidance.
You do not need to manually check permissions when vetting AI coding skills, as the automated workflow evaluates permission scopes and network access as part of its mandatory structured vetting process.
polaris-dxzAutomate security vetting of AI agent skills before installation.
Science-DiscoveryAudit AI Skill packages for security risks and output PASS/WARN/FAIL reports.
jikig-aiScan git-diff-selected source files with semgrep for vulnerability patterns.
bcastelinoScan codebases and infrastructure for security vulnerabilities with Python scripts.
