ClawHub
Back to skill

Security audit

Qcsd Quality Gates

Security checks across malware telemetry and agentic risk

Overview

This is a code-quality helper, but it tells the agent to run broadly and change project files without clear confirmation or boundaries.

Install only if you want an agent to aggressively enforce quality gates and potentially edit dependencies, imports, syntax, configuration examples, and missing files. Use it under version control and require explicit confirmation or a dry-run before accepting automatic repairs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (4)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The README explicitly authorizes automatic modification and creation of project files based on error analysis, but it does not warn users about the scope of changes, the possibility of destructive edits, or the need for confirmation/backup before remediation. In an agent skill context, this increases the risk of unintended code, configuration, or data loss because the agent may change files beyond what the user expected.

Vague Triggers

High
Confidence
95% confidence
Finding
The trigger conditions are mandatory and extremely broad, including 'every time outputting code to the user' and 'every new project', which can cause the skill to activate during routine development without explicit user consent. Because the skill also advertises automatic repair capabilities that modify code, dependencies, and files, unintended invocation can lead to unreviewed project changes, workflow disruption, and possible damage to repositories or environments.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill describes extensive automatic fix behavior, including changing dependencies, correcting imports, fixing syntax, creating files, and responding to startup failures, but it does not warn users that their codebase may be modified automatically. This lack of disclosure increases the risk of surprise changes, unsafe edits, and accidental repository state corruption, especially when combined with the broad mandatory triggers earlier in the document.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "pejic",
  "license": "MIT",
  "devDependencies": {
    "jest": "^29.7.0"
  }
}
Confidence
92% confidence
Finding
The devDependency uses a caret range (^29.7.0), which allows automatic installation of newer compatible versions rather than a single fixed version. This can introduce supply-chain risk if an upstream release is compromised or if builds become non-reproducible, though the impact here is limited because it is only a test dependency in package.json.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.