Security audit

Yq Hot Topic Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed hot-topic research and article-writing workflow, with expected web searches and local article files but a few user-control caveats.

Install if you are comfortable with a skill that performs web research, creates markdown/docx article files in the workspace, may update them during fact-checking, and may reuse the previous topic in scheduled runs. Avoid giving it sensitive private topics unless you are comfortable with those terms being searched, and check for existing article files with the same date before running it.

SkillSpector

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 (2)

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill instructs the agent to save and later modify article files on disk, but it never tells the user that files will be created and potentially updated during fact-checking. This can cause unexpected persistence and silent overwrites, especially in shared or automated environments where users may assume the output is only conversational.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The scheduled-task section says the skill will automatically continue tracking the previous topic, which implies reuse of prior user context without an explicit privacy or consent boundary. In recurring jobs, this can leak or misuse retained interests, search history, or prior task state beyond what the current invocation clearly authorizes.

Static analysis

No suspicious patterns detected.