Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:401
Security audit
TrustBoost PII Sanitizer
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed remote PII-sanitizing API skill with no local executable code, but it sends raw text to a third-party service and supports paid usage.
Install only if you are comfortable sending raw text to TrustBoost before redaction. Do not submit production secrets, private keys, passwords, or regulated records unless the external processing and retention policy are acceptable. Use trial mode first and set explicit limits before allowing any autonomous paid Solana transaction.
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.prompt_injection_instructions