Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:579
Security audit
Writing Skills
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are high-capability but coherent, explicit, and scoped to ClawHub/Convex maintenance, moderation, documentation, and review workflows.
Install only if you are comfortable with repo-maintenance skills that can invoke authenticated ClawHub/Convex/GitHub tools and external AI review CLIs. For moderation, email, migrations, and production actions, check the exact command, target, reason, and dry-run output before approving any write.
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