Back to skill

Security audit

CaptainBI

Security checks for vulnerabilities and agentic risk

Overview

The CaptainBI workflow fits its purpose, but setup can execute unverified remote code without asking first.

Review and approve a fixed CLI release before allowing setup. Check its automatic skill synchronization and disable it if unwanted. Connect only the intended CaptainBI account and understand that OOMOL mediates access to its business data. The bundled instructions were fully inspected; remote installer and connector behavior remain unverified. No malicious behavior was established.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command performs remote software installation rather than searching or reading CaptainBI data. Nothing in the provided chunk establishes that this installer is a necessary supporting component for CaptainBI access. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote installer directly into bash executes its contents with the invoking user's privileges, without a pinned version or independent integrity verification. If the distribution endpoint or release pipeline is compromised, the installer could access local secrets or modify files; HTTPS and the legitimate dependency relationship do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback directs the agent to execute a remote installer without explaining that this runs third-party code locally or requiring explicit installation approval. Triggering setup only when the CLI is missing reduces exposure, but a request to read CaptainBI data does not itself authorize arbitrary local installation and its potential filesystem or environment changes.

Content

No source excerpt is available for this finding.

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 84)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