Security audit
Claude Code Security Scan
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward security-audit skill that tells the agent how to run a third-party scanner, with no hidden executable code bundled in the skill itself.
Install only if you are comfortable running ecc-agentshield from npm. Prefer npx or a pinned package version, scan only the intended Claude configuration path, review changes before using --fix or init, and avoid the optional ANTHROPIC_API_KEY deep-analysis mode for sensitive configs unless external analysis is acceptable.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.