ClawHub

Gh Standup

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward GitHub standup helper that reads PR and commit activity through the user's authenticated GitHub CLI and prints a summary.

Before installing, confirm you are comfortable with it using your current gh CLI login to read GitHub activity. Prefer --repo for narrow summaries; use --org only when you intend to scan all accessible repos in that organization, and review the generated text before sharing because it may include private repo names, PR titles, commit messages, and links.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
75% confidence
Finding
The description uses broad triggers like 'work summary', 'weekly update', and 'what did I do since [day]', which can match many ordinary summarization requests that do not imply consent to query GitHub. This can cause the skill to activate unexpectedly and pull repository or organization activity when the user may have intended a non-GitHub summary.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill can query a whole repository set or an entire organization through an authenticated `gh` session, but the description does not clearly warn users about that scope. In context, this increases the risk of over-collection and unintended disclosure of work activity across multiple repos, especially when `--org` is used.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal