Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- scripts/test-credibility-coordinator.mjs:29
Security audit
Credibility Action Gate
Security checks across malware telemetry and agentic risk
Overview
This skill is a local analysis tool for credibility checks and does not itself spend funds, access credentials, call external services, or run in the background.
Install only if you are comfortable using a local Node script to process claim-review JSON and operator policy. Review the generated disposition before taking any real-world action, because the skill intentionally advises on eligibility but does not verify facts, move funds, or make the final mission decision.
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
64/64 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.dangerous_exec