ClawHub
Back to skill

Security audit

Mailcoach

Security checks for vulnerabilities and agentic risk

Overview

The Mailcoach controls are sensible, but setup instructs the agent to run unverified downloaded installers without first seeking separate approval.

Review and install the CLI separately using a verified release before enabling this skill. Connect only the intended Mailcoach account and retain its approval requirements for changes and deletions. The review concern is the automatic installer fallback; no malicious behavior was established. The installer contents and external connector implementation were not verified.

A.I.G

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

SkillSpector

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
98% confidence
Finding

The supplied code performs no visible Mailcoach operation. Instead, it executes an external installer, and nothing supplied establishes that installer as a supporting dependency for Mailcoach. The remote script's contents are unavailable, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote response directly into Bash without verifying a pinned artifact, signature, or trusted checksum. Compromise of the distribution endpoint could therefore execute arbitrary code with the invoking user's privileges; HTTPS and the legitimate dependency relationship do not protect against a compromised publisher or distribution service.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local system changes.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback directs installation of local software without requiring explicit approval or explaining the installer's system changes. A Mailcoach data-operation request does not inherently authorize executing an installer with the user's local privileges; the missing-command condition limits exposure but does not establish consent.

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 88)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