ClawHub
Back to skill

Security audit

Code Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent code-audit skill that reads repository context for audits and does not show hidden, destructive, or deceptive behavior.

Install this if you want an agent to perform repository audits. Treat audit snapshots and packets as potentially sensitive because they can include local paths, branch names, changed-file names, and diff stats; use .auditignore/skip paths and avoid external reviewer routes unless your repository policy allows sharing code or metadata.

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
82% confidence
Finding
The script emits repository root, branch name, git status, diff stats, ignore patterns, and sampled file paths directly to stdout/JSON without any explicit consent gate, redaction, or warning at the point of output. In an audit skill context, this can expose sensitive repository metadata, internal filenames, feature names, or change activity to downstream logs, agents, or users who did not intend that level of disclosure.

Static analysis

No suspicious patterns detected.