ClawHub
Back to skill

Security audit

incremental-implemen

Security checks across malware telemetry and agentic risk

Overview

This skill is a broad development automation helper that can read files and run commands, but its scope and safeguards are too vague for the authority it requests.

Review this carefully before installing. It is not evidence of malware, but it grants a coding agent broad read and command authority for ordinary multi-file changes; use it only in repositories where command execution and credential use are acceptable, and avoid exposing sensitive environment variables unless the workflow is clearly understood.

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
90% confidence
Finding
The activation text is extremely broad, encouraging use for 'any feature or change that touches more than one file' and general efficiency/automation scenarios. In an agent ecosystem, this can cause the skill to auto-trigger in many ordinary coding tasks and implicitly gain access to read/exec capabilities more often than users expect, increasing the chance of unintended file changes or command execution.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill describes file handling, command execution, API-key configuration, and external calls, but does not present a prominent user warning or consent checkpoint about these high-impact actions. Because the skill also advertises automation and broad applicability, users may invoke it without realizing it can modify files, run commands, or use credentials, which raises the risk of destructive changes, secret exposure, or unintended external interactions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.