Agent Daily Report (EN)
Security checks across malware telemetry and agentic risk
Overview
This skill only instructs an agent to summarize its own work activity into a daily report, with no hidden code or unrelated access requested.
Safe to install for personal daily reporting. Review generated reports before sharing them, because they may include task names, filenames, tools used, retrieved information, blockers, or other work details.
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.