Security audit
AANA Support Reply Guardrail Skill
Security checks across malware telemetry and agentic risk
Overview
The skill text is a normal support-reply safety checklist, but its marketplace capability tags claim wallet, purchase, transaction-signing, and sensitive-credential access that does not fit that purpose.
Read the requested capabilities carefully before installing. The written skill appears safe as a checklist, but do not grant wallet, transaction-signing, purchase, or sensitive-credential authority unless the publisher corrects or clearly explains those tags, or your environment can block those capabilities.
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.