ClawHub

Issue Prioritizer

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate GitHub issue triage skill, but it grants broader authenticated GitHub command access than a read-only analyzer needs.

Install only if you are comfortable with the skill running under your authenticated GitHub CLI session. Prefer a fine-grained or read-only GitHub token, avoid using it on sensitive private issue trackers, and ask the publisher to narrow allowed tools to read-only commands such as `gh issue list/view` and `gh pr list/view`.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
85% confidence
Finding
The skill is described as a read-only GitHub issue prioritizer, but the optional deep-analysis section instructs the agent to send issue content to an external LLM/API. That expands the trust boundary and can expose potentially sensitive repository data, private issue details, or prompt-injection content to a third party without being necessary for the core GitHub CLI-based functionality.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger prompts are fairly broad and map to common issue-triage language such as prioritizing bugs, ranking issues, and finding quick wins. Without tighter activation constraints, the skill may trigger on generic GitHub or project-management requests, causing misrouting, unintended data access within its read scope, or bypass of more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal