ClawHub
Back to skill

Security audit

Google Photos

Security checks across malware telemetry and agentic risk

Overview

This skill transparently lets an agent operate Google Photos through OOMOL, with sensitive write/delete actions disclosed and gated by confirmation instructions.

Install this only if you want an agent to access Google Photos through OOMOL. Treat uploads, album updates, description changes, picker-session deletion, and downloads as sensitive, and approve write or destructive payloads only after checking the exact target and effect.

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
93% confidence
Finding
The skill description says to use this skill for ANY Google Photos request, which is broad enough to auto-route unrelated or insufficiently scoped requests whenever Google Photos is mentioned. In an agent setting, this can cause over-selection of a write-capable skill and increase the chance of unnecessary data access or unintended state-changing operations against the user's Google Photos account.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.