ClawHub
Back to skill

Security audit

SatisMeter

Security checks for vulnerabilities and agentic risk

Overview

This SatisMeter skill is mostly a bounded read-only OOMOL connector, but its setup instructions include unsafe direct execution of remote installer scripts.

Review the setup path before installing. Use a safer verified or package-manager install for the oo CLI where possible, avoid running remote scripts directly into bash or PowerShell, and be aware that SatisMeter requests will be handled through OOMOL's connector service.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:60
Finding

Unverified Remote Installer Scripts Executed Directly by Shell Interpreters

Content
View full analysis
Remediation
View remediation
" echo " oo-installer.sh" | sha256sum --check - less oo-installer.sh bash oo-installer.sh ``` 9. Apply equivalent download, Authenticode/signature, and checksum verification controls to the PowerShell installer. ]]>

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 (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install the CLI via 'curl ... | bash', which executes a remote script directly without integrity verification or review. If the install endpoint, network path, or hosting is compromised, this becomes arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for 'ANY SatisMeter request' and 'instead of calling the API directly,' which is an overly broad routing instruction. That can cause unintended activation for loosely related prompts and may steer the agent into running connector-backed commands without sufficient task-specific validation, increasing the chance of unnecessary data access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.