User-controlled placeholder is embedded directly into generated source code.
Critical
- Code
- suspicious.generated_source_template_injection
- Location
- SKILL.md:23
Security audit
Product Data Collection
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for a product data task API; it uses an auth token and can change remote task records, but those abilities are clearly disclosed and match its purpose.
Install only if you trust the product-task API and can provide a properly scoped authorization value. Treat create, update, and batch-update as actions that can change remote data, verify filters and target environment before use, and keep PRODUCT_TASK_AUTH out of chats, logs, screenshots, and source files.
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
65/65 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.generated_source_template_injection