Agentic Paper Digest Skill

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a legitimate paper-digest helper, but its local helper scripts are broader than users may expect when loading environment files and stopping services.

Install only if you trust the linked GitHub project and are comfortable reviewing downloaded code and dependencies. Use a limited API key, keep .env private, do not point ENV_FILE at untrusted files, and check what is using port 8000 before running the stop script.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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: 89% confidence
Finding: The skill tells users to create and populate a .env file with API credentials but provides no warning that the file contains secrets or guidance on preventing accidental exposure. In a workflow that clones repositories, edits config, and may run API servers, this increases the risk of credential leakage through version control, logs, shared workspaces, or permissive file handling.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal