Back to skill

Security audit

OOMOL RAG

Security checks for vulnerabilities and agentic risk

Overview

The knowledge-base workflows are well scoped, but setup runs unverified downloaded code and omits the CLI’s documented changes to installed agent skills.

Review and approve CLI installation separately before using the fallback. Check which bundled agent skills it installs or synchronizes, and disable startup synchronization if unwanted. Confirm the intended OOMOL team and protect temporary public export links. The sole bundled artifact was fully inspected; the remote installers remain unverified.

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
88% confidence
Finding

The supplied chunk performs CLI installation and contains no OOMOL RAG operations. Although a CLI installer could support the declared workflow, the supplied content does not establish that connection or disclose installation as its purpose. The remote script's contents are unavailable, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remote response directly into Bash executes mutable network-delivered code without an integrity check or review opportunity. HTTPS protects transport but does not protect against a compromised publisher or distribution infrastructure; exploitation could compromise files and credentials accessible to the invoking user.

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

Automatic CLI setup executes remotely downloaded scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to execute downloaded installation scripts without explicit approval for local system changes or verification of the script's integrity. Although conditional and hosted on a vendor-related HTTPS domain, it can execute arbitrary code with the invoking user's privileges if the distribution endpoint is compromised; this overlaps with SC2.

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 136)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