ClawHub
Back to skill

Security audit

InfluxDB Cloud

Security checks for vulnerabilities and agentic risk

Overview

The database workflow is controlled, but setup executes unverified downloads and the required CLI can make persistent changes to other agent skills.

Review setup before installing. Install a verified CLI version yourself and disable its startup skill synchronization using OO_SKILLS_SYNC_DISABLED=1 before agent use. Use a limited-scope InfluxDB token and retain the required write confirmations. The single bundled file was fully reviewed, but the remote installers and deployed connector were not verified.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code runs an Oomol-hosted installer, which is materially different from the declared InfluxDB Cloud data-management purpose. Nothing in the chunk establishes that this installer is a supporting dependency for InfluxDB operations. The downloaded script's contents and subsequent effects cannot be determined from the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a mutable remote script directly into Bash, with an equivalent download-and-execute pattern for PowerShell, without version pinning or independent integrity verification. If the distribution endpoint or release pipeline is compromised, attacker-controlled code could execute with the agent's local permissions and access files or credentials. Installation is conditional on a missing CLI, which reduces exposure but does not make execution safe.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources