ClawHub
Back to skill

Security audit

Experiment Readout

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped A/B test readout helper that asks for experiment data and produces statistical analysis without hidden access, persistence, or system changes.

Installers should know this skill may influence product decisions, so review its statistical assumptions and verify calculations independently for high-stakes launches; also note that the referenced helper script is not included in the package.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says to use the skill when asked to 'analyse experiment results' or 'decide ship/no-ship from test data,' which are broad activation cues without clear scope boundaries or exclusions. It does not define narrower trigger phrases or negative examples, so the skill could be invoked for loosely related analytics discussions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.