Back to skill

Security audit

Predis.ai

Security checks for vulnerabilities and agentic risk

Overview

The Predis.ai integration is coherent, but its setup instructions can trigger remote software installation without clear approval or disclosure of the changes.

Review and approve CLI installation separately before allowing setup to run. Verify the installer and check whether it will install other agent skills. Connect only the intended Predis.ai account and understand that requests pass through OOMOL. The complete bundled skill was inspected, but the external installer and hosted implementation remain unaudited.

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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied chunk installs software from an unrelated service and shows no Predis.ai interaction. Nothing in the provided content establishes this installation as a supporting requirement for the declared Predis.ai functionality. The downloaded script's subsequent behavior is not visible.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The supplied chunk performs only an oo login and contains no identifiable Predis.ai integration or data operations. Authentication could support an integration, but nothing in this chunk establishes that relationship; its visible purpose differs from the declared Predis.ai functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the installer URL directly into Bash executes mutable remote content without pinning, integrity verification, or an opportunity to inspect it. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from delivering code that runs with the invoking user's privileges; the legitimate setup purpose does not remove this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup instructions direct execution of downloaded shell or PowerShell code without explicit approval for local installation or an explanation of the system changes. Although triggered only when the CLI is missing, this can turn a Predis.ai request into local code execution with the invoking user's privileges; compromise of the installer could expose accessible files and credentials.

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 78)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