ClawHub

Daily Standup Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only standup report helper that uses local git and GitHub activity in ways that match its stated purpose, though it can surface private development details.

Install this only if you are comfortable letting the agent read activity from the intended repositories and the currently authenticated GitHub CLI account. Specify the repo paths, author, time range, and whether team mode is intended, and review the generated report before sharing because it may include branch names, uncommitted work, PR links, issue details, reviewer names, or internal blockers.

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
94% confidence
Finding
The manifest trigger phrases are broad enough to match common requests like 'status update' or 'daily report', which can cause the skill to activate in contexts where the user did not intend repository, PR, or issue-tracker analysis. Because the skill gathers local git identity, branch state, uncommitted work, and hosted account activity, accidental invocation can expose sensitive development metadata without a clear, explicit opt-in at the moment of use.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill performs extensive collection of repository and account activity, including git config identity, commit history, branch names, stash contents, PR metadata, issue assignments, and potentially team-wide activity, but the description does not clearly warn the user about this scope. In context, this increases privacy and confidentiality risk because the data can include sensitive project names, internal URLs, reviewer identities, blockers, and uncommitted work that the user may not expect to be inspected or summarized.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal