ClawHub
Back to skill

Security audit

FastMoss MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using FastMoss through OOMOL, but its first-time setup tells an agent to run unverified remote installer scripts.

Install only if you trust OOMOL and intend to use an OOMOL-connected FastMoss account. Do not let an agent run the curl|bash or irm|iex installer automatically; download from the vendor, verify the installer where possible, and approve any write/destructive FastMoss action only after reviewing the exact target and payload.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
97% confidence
Finding
The skill instructs users or an agent to install software via `curl ... | bash`, which executes remote script content directly without prior verification. If the distribution endpoint, transport, DNS, or hosting is compromised, arbitrary code would run on the local system with the user's privileges; in an agent setting, this is especially dangerous because the skill frames it as an automatic recovery step after command failure.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use this skill for "ANY FastMoss MCP request" and whenever a task involves FastMoss MCP, without narrowing scope or giving exclusion examples. That activation wording is broad enough to match many routine mentions of FastMoss and does not specify boundaries for when the skill should not be invoked.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The action description states that `search_category_by_words` returns matched category IDs and Chinese category paths, which imposes a locale-specific output format without indicating user choice or opt-in. This can conflict with language/locale policy expectations when users have not requested Chinese output.

Static analysis

No suspicious patterns detected.