Agentsop Bio Fraud Forensics

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed biomedical research-integrity screening guide with strong neutral-language safeguards and no executable code, hidden install behavior, or credential collection.

Install only if you want an automatically available biomedical paper-integrity screening assistant. Treat outputs as preliminary observations, verify any cited evidence yourself, and keep any public or editorial comments neutral, reproducible, and non-accusatory.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The documented trigger phrases are very broad, including common conversational terms like '检查/筛查' and '去哪查', which increases the chance the skill activates in situations the user did not intend. In an auto-loaded environment, unintended activation can cause the agent to shift into a sensitive forensic-analysis workflow, potentially producing reputationally risky output or consuming tools/resources on unrelated biomedical content.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal