Algolia

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Algolia connector skill that can read and change Algolia data through OOMOL, with no evidence of hidden code, exfiltration, or automatic destructive behavior.

Install this only if you trust OOMOL to broker your Algolia connection and you are comfortable giving the connected API key the listed scopes. Review payloads carefully before approving writes, rule or synonym saves, and especially filtered deletes, because those can affect production search data.

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: 89% confidence
Finding: The trigger text is overly broad and instructs use of this skill for ANY Algolia-related request, which increases the chance of unintended invocation when Algolia is only tangentially mentioned. Because the skill exposes both read and state-changing actions, over-selection can route users into unnecessary or risky flows and increase the chance of accidental modification or deletion operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal