Daily Log

Security checks across malware telemetry and agentic risk

Overview

This daily logging skill is transparent about writing persistent work notes, but users should avoid letting it save secrets or sensitive task details.

Install only if you want the agent to maintain persistent daily work logs. Review or redact entries before saving, especially command output, errors, file paths, customer data, credentials, tokens, and proprietary details that should not be reused by later memory workflows.

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

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly instructs the agent to write or merge content into `memory/daily/YYYY-MM-DD.md` but does not warn the user that it will modify local state. Silent file creation or modification can surprise users, persist sensitive conversation details, and create privacy or compliance issues if the log includes confidential task content.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal