Fossil Record

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Git history analysis skill, with the main caution that one trigger phrase is too broad and repository history may contain sensitive old information.

Install this only if you want an agent to inspect Git history for the current repository. Use explicit prompts about Git history or code evolution, and avoid running it on repositories whose old commits may contain secrets or sensitive internal context.

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
92% confidence
Finding
The invocation guidance includes a trigger based on ordinary conversation ('When someone asks "why?"'), which is overly broad and can cause the skill to activate in many contexts unrelated to git-history analysis. This increases the chance of unintended execution, unnecessary repository inspection, and prompt-scope drift when a casual question is interpreted as a request to run the skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal