Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:44
Security audit
we
Security checks for vulnerabilities and agentic risk
Overview
No artifact-backed harmful behavior was found; the available signals show a clean SkillSpector result, pending VirusTotal telemetry, and only an unverified prompt-injection indicator.
Install only if the published skill text and metadata match what you expect. Because VirusTotal is still pending and a prompt-injection indicator was noted, review the skill instructions for any unrelated role changes, hidden commands, credential requests, or automatic actions before use.
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
Static analysis
Detected: suspicious.prompt_injection_instructions