ClawHub
Back to skill

Security audit

Pinecone

Security checks across malware telemetry and agentic risk

Overview

This Pinecone connector skill is purpose-aligned and clearly discloses its read, write, and destructive capabilities.

Install this only if you intend to let Codex operate your Pinecone account through OOMOL. Review write and delete payloads carefully before approving them, especially delete_index, delete_vectors, update_vector, and upsert_vectors. Ensure you trust the oo CLI and OOMOL connection model before completing first-time setup.

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 skill description says to use this skill for ANY Pinecone request and instead of calling the API directly, which is an overly broad routing rule. This can cause the agent to invoke a high-privilege connector for benign or ambiguous Pinecone-related tasks, increasing the chance of unintended data access or state-changing operations without sufficient task-specific safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.