ClawHub
Back to skill

Security audit

WaitingForMacGuffin

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Oscar prediction-market skill that fetches public data and may provide betting-style analysis, so users should treat it as gambling-related guidance rather than financial advice.

Install only if you want Oscar prediction-market and betting-related analysis. Treat outputs as informational, verify legality and eligibility in your jurisdiction, avoid relying on it as financial advice, and be aware it can call an external public API with curl.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill's opening description and onboarding emphasize 'best Oscar bets,' ROI, and portfolio construction without an upfront warning that it provides gambling-related recommendations. Users can be funneled into actionable betting guidance before seeing any meaningful disclaimer, which raises consumer protection and responsible-gambling concerns.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly switches into bet recommendation mode based on broad natural-language triggers like 'what should I bet on' and 'best picks,' then generates portfolio-style gambling advice. In a skill centered on prediction markets, this increases the chance that ordinary informational queries are nudged into personalized wagering guidance, which can create compliance, safety, and suitability issues.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.