File appears to expose a hardcoded API secret or token.
Critical
- Code
- suspicious.exposed_secret_literal
- Location
- SKILL.md:37
Security audit
Scavio Google News
Security checks across malware telemetry and agentic risk
Overview
This skill bundle uses powerful admin and observability tools, but the behavior is disclosed, task-focused, and gated by user credentials and confirmations.
Install only if you intend to give the agent operational access to these systems. Use least-privilege tokens, review destructive commands before approval, and be especially careful with Slack posting, ClawHub staff actions, production deploys, and Axiom/Grafana deletion commands.
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
63/63 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.exposed_secret_literal