Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:596
Security audit
Skill Security Reviewer 3.0
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed read-only skill-review workflow that analyzes other skills and writes a local report, with no evidence of hidden execution, exfiltration, or persistence.
Install this only if you want an agent to inspect other skills. Expect it to read the selected target skill's files and create a local report that may contain decoded or suspicious snippets, so treat reports as potentially sensitive.
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
66/66 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions