ClawHub
Back to skill

Security audit

Retently

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Retently connector wrapper with scoped commands and confirmation guidance for writes.

Install this only if you intend to let Codex access your Retently data through OOMOL. Review write payloads carefully before approval, especially bulk customer upserts, and only run the oo CLI setup or account connection steps if you trust OOMOL and the connected Retently account.

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
91% confidence
Finding
The skill instructs the agent to use this skill for ANY Retently-related request instead of calling the API directly, which is an overly broad trigger phrase that can override normal tool-selection judgment. This can cause inappropriate invocation in edge cases, increase unnecessary exposure of Retently data/operations, and reduce the chance that safer or more context-appropriate handling is chosen.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.