Security audit
Github Webhook Architect
Security checks across malware telemetry and agentic risk
Overview
This skill is not malware, but it should be reviewed because it can set up GitHub events that trigger an agent to act with broad GitHub authority.
Install only if you are comfortable running an externally triggered GitHub automation path. Use HTTPS only, least-privileged GitHub tokens and agents, narrow workflow triggers, verified actor checks from signed GitHub webhook/API data, an allowlisted command schema, and human approval before repository-writing actions.
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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.