Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- skill.js:50
Security audit
AOI Triple Memory (Lite)
Security checks across malware telemetry and agentic risk
Overview
This skill appears to do its stated local memory/search job, but it deserves review because it searches workspace files, writes notes, depends on undeclared ripgrep, and has a reported ripgrep option-injection risk.
Install only if you are comfortable with a skill searching the entire selected workspace and writing notes under ./context. Avoid using it in repositories with secrets or private configs unless you restrict the workspace, and prefer a fixed version that declares ripgrep and passes the search pattern after an rg option delimiter such as --.
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