ClawHub
Back to skill

Security audit

Apify

Security checks across malware telemetry and agentic risk

Overview

This Apify connector is mostly coherent, but it can start Apify actor runs through a connected account while its safety labeling treats untagged actions as safe reads.

Review this skill before installing. It is not showing malware or hidden code, and VirusTotal/static scans were clean, but install it only if you trust OOMOL’s oo CLI and account connection model. Before any run_actor use, require explicit approval of the actor, input payload, expected cost/resource impact, and resulting data access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description says to use this skill for "ANY Apify request," which is an overly broad activation trigger. That can cause the agent to invoke this skill in situations where a narrower or safer tool should be used, increasing unintended execution and expanding the attack surface for connector-backed actions, including state-changing ones like `run_actor`.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.