Back to skill

Security audit

Fireberry

Security checks for vulnerabilities and agentic risk

Overview

The Fireberry workflow requires approval for data changes, but setup can execute unverified remote code without separate installation approval.

Review the setup before use. Install a verified CLI yourself rather than allowing automatic remote-script execution. OOMOL will mediate access to your Fireberry data; connect only needed permissions and approve exact changes or deletions. The sole bundled artifact was fully inspected, but remote installer and connector behavior 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
97% confidence
Finding

The supplied chunk performs remote installer execution, not Fireberry data management. Although installation can be a supporting implementation detail, nothing in this chunk establishes that this installer supports Fireberry. The remote script's contents are not supplied, 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 an HTTPS response directly into bash executes mutable remote content without verifying or reviewing it. Although the endpoint is consistent with the documented CLI provider and installation is conditional, compromise of the hosting infrastructure or release pipeline could allow code execution and access to local data with the agent's privileges.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

The setup workflow instructs execution of remotely downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs the agent to execute remotely supplied shell or PowerShell code without review, integrity verification, or explicit approval for local installation. The missing-CLI condition limits exposure, but a compromised installer source could execute arbitrary code with the invoking user's privileges; 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 86)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