Back to skill

Security audit

Referral Rock

Security checks for vulnerabilities and agentic risk

Overview

The Referral Rock actions are appropriately limited, but setup allows remote code execution and broader agent changes without clearly scoped user approval.

Review and install a verified CLI release yourself before enabling this skill. Decide whether its automatic installation and synchronization of other agent skills is acceptable, and disable that behavior if unwanted. OOMOL is an explicitly disclosed intermediary for your connected Referral Rock account. The bundled instructions were fully reviewed, but the remote installers and deployed connector implementation were not verified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command runs a remote installer, which is materially different from the declared Referral Rock search-and-read functionality. Nothing in the supplied chunk establishes this installation as a necessary supporting implementation detail. The downloaded script's contents and any further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an unpinned HTTPS response directly into Bash executes whatever the endpoint returns, without an artifact integrity or authenticity check beyond transport security. A compromised endpoint or malicious installer update could execute arbitrary code with the agent's privileges; the legitimate setup context limits when this occurs but does not remove the risk, and this overlaps with SQP-2 rather than representing a separate exploit.

Content

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

Setup instructs the agent to execute remotely downloaded installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs the agent to execute downloaded shell or PowerShell code without first obtaining informed approval or verifying the downloaded artifact. Although installation is conditional and legitimately supports the connector, it can modify the host with the executor's privileges if the installer or its distribution infrastructure is compromised.

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 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

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
## Resources

- Referral Rock homepage: https://referralrock.com
- API documentation: https://api.referralrock.com/help