Back to skill

Security audit

Benchmark Email

Security checks for vulnerabilities and agentic risk

Overview

The email-reading functions fit the stated purpose, but automatic setup executes downloaded code without integrity verification or a clear approval step.

Review and authorize CLI installation separately, including its automatic installation and synchronization of agent skills. Prefer a verified installation before using this skill, and connect only the intended Benchmark Email account. OOMOL mediates access to contact data. No malicious payload was established, but the remote installers were unavailable for inspection.

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
96% confidence
Finding

The supplied chunk performs remote script execution rather than any visible Benchmark Email operation. Although installing a CLI could be a supporting implementation detail, nothing supplied establishes that this installer supports the declared service. The downloaded script's contents and any further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash pipeline executes the response from a mutable remote endpoint without inspecting it or verifying an expected artifact. HTTPS protects transport but does not prevent malicious changes at the distribution endpoint, so compromise could expose locally accessible files and credentials; the legitimate CLI dependency and missing-command trigger reduce suspicion, not the execution impact.

Content

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

Automatic CLI setup executes remote installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

When the CLI is missing, the skill directs installation by immediately executing downloaded shell or PowerShell content without requiring user approval or integrity verification. Installation is conditional rather than routine, which reduces exposure, but a compromised installer could execute arbitrary code with the invoking user's permissions.

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