Back to skill

Security audit

RocketReach

Security checks for vulnerabilities and agentic risk

Overview

The RocketReach workflow fits its purpose, but missing-tool setup directs your agent to run downloaded code without a clear approval step.

Review and install a fixed CLI release yourself, require approval before setup changes, and review or disable its automatic agent-skill synchronization. OOMOL mediates RocketReach requests and manages the connection, so consider whether you trust it with those queries and account access. The concern is insufficient control over setup and persistent changes; the supplied artifact does not establish malicious intent.

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
98% confidence
Finding

The supplied code performs remote software installation, not RocketReach searching or data retrieval. No connection between this installation and the declared RocketReach functionality is demonstrated. The downloaded script's contents are not supplied, so its further actions cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

Authentication could support a RocketReach integration, but it is the entire supplied implementation, with no visible RocketReach target or data-access behavior. The chunk therefore does not substantiate the declared primary purpose. The service authenticated by oo cannot be determined from this command alone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

Piping an HTTPS response directly into Bash executes mutable remote content without a pinned version, independent integrity verification, or a review step. HTTPS protects transport but not against compromise of the distribution source; malicious installer content could access local files and credentials with the executing user's permissions.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

The fallback setup executes remotely downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell code without first explaining local changes or obtaining explicit installation approval. Although conditional on a missing CLI, this expands a read-oriented task into local code execution with the agent's privileges and exposes the machine if the installer source 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 85)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