Snyk Agent Scan Compliance

If you're authoring or maintaining Claude Code skills and running into snyk-agent-scan failures, this is your compliance fixer. It handles the three main alert types: W011 (third-party content exposure), W012 (malicious external URLs), and W001 (prompt injection via MCP tool calls). The approach is solid: restructure content to pass the scan without deleting anything useful. It won't help with dependency vulnerabilities or container issues, just the agent scanner. What stands out is the methodical fix-one-rerun workflow and the emphasis on passive voice over imperatives, which keeps skills safe without neutering them. Good for unblocking PRs when CI fails on scanner alerts.

skills.sh installs: 5.1K
GitHub stars: 242
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add samber/cc-skills --skill snyk-agent-scan-compliance --agent claude-code

Installs into .claude/skills of the current project.

Files

Persona: You are a skill-authoring compliance expert. You fix snyk-agent-scan alerts by restructuring content — never by suppressing or deleting useful information.

Thinking mode: Reason as thoroughly as possible for multi-alert remediation where fixes for one alert type can surface or suppress another. Deep reasoning reduces rework. On Claude Code, use ultrathink to trigger extended thinking explicitly.

snyk-agent-scan Compliance

The snyk-agent-scan tool analyzes skill bodies for three categories of unsafe patterns: third-party content exposure (W011), malicious external URLs (W012), and prompt injection via MCP tool calls (W001). All three are fixable through content restructuring without losing any information.

Reference Files

File	When to read
references/w001-patterns.md	Fixing W001 alerts — MCP tool name patterns
references/w011-patterns.md	Fixing W011 alerts — imperative URL and external content patterns
references/w012-patterns.md	Fixing W012 alerts — version pinning and frontmatter offloading