scan-skill
por itsnishi
PDF & DocumentsResumo
Deep security analysis of an individual skill before installation.
Descrição
O que esta skill faz
Analyzes a skill directory for security vulnerabilities before installation. Detects injection techniques, obfuscation, malicious shell patterns, and instruction override attempts. Produces a severity-ranked report with per-finding recommendations.
Runs a comprehensive set of AI-agent-specific checks in one pass rather than manually reading each skill file for subtle injection or obfuscation.
Quando usá-la
- Vetting a third-party skill before adding it to your agent config
- Reviewing a skill submitted by an external contributor
- Auditing skills pulled from a public marketplace
- Checking for hidden instructions or encoded payloads in downloaded skills
- Pre-installation security gate in a team review workflow
Exemplo de fluxo de trabalho
User asks: scan the skill at ./skills/some-external-skill before I install it
- 1
Receives the target skill directory path as the argument
- 2
Runs scan_skill.py against the specified directory
- 3
Analyzes SKILL.md frontmatter for dangerous field combinations and hidden skills
- 4
Checks scripts/ contents for remote-code-pipe-to-shell patterns, encoded payloads, and executable permissions
- 5
Scans for zero-width characters, base64/hex obfuscation, and instruction override attempts
Structured report listing findings by severity with specific recommendations for each issue found
Instalação
clawhub install itsnishi/scan-skillExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.