ClawHub
Back to skill

Security audit

ia-md-docs

Security checks across malware telemetry and agentic risk

Overview

This documentation skill is mostly coherent, but it gives agents broad authority to edit persistent agent context files and verify commands in ways users should review first.

Review proposed changes before allowing writes, especially AGENTS.md and CLAUDE.md. Use dry-run where possible, confirm before replacing or symlinking existing files, and do not allow the skill to run deploy, migration, credentialed, or otherwise state-changing commands just to verify documentation unless you explicitly intend that.

SkillSpector

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

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The workflow directs the agent to write AGENTS.md and force-create a CLAUDE.md symlink using `ln -sf`, which can overwrite or replace existing files without an explicit confirmation step at the point of modification. In a documentation-management skill, file writes are expected, but doing so silently increases the risk of unintended data loss or project-state changes, especially when auto-derived content may be wrong or incomplete.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.