ClawHub
Back to skill

Security audit

Polymarket Odds 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Polymarket lookup CLI that makes disclosed public read-only requests, with minor scoping and documentation cautions.

Install only if you are comfortable with the agent sending market search terms to Polymarket. Use it for Polymarket or prediction-market odds, not private or sensitive questions that merely ask about probabilities.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Ae1

High
Category
analysis-evasion
Content
The CLI is at `polymarket.mjs` in this skill folder. Run with:
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill clearly instructs the agent to use a CLI that performs outbound network requests to public Polymarket endpoints, but the manifest does not declare any tool scope, permissions, or allowed-tools constraints. This creates a governance gap: an agent may invoke network-capable code without explicit user-visible authorization boundaries, increasing the chance of unintended external requests or misuse in environments that rely on manifest-level restrictions.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description says to use the skill when asked about odds, probabilities, predictions, or 'what are the chances of X,' which is broad enough to trigger on many unrelated requests. Overbroad invocation criteria can cause the agent to inappropriately route general probabilistic or predictive questions to this networked skill, leading to unnecessary external calls, irrelevant outputs, or data leakage through query terms sent to third-party services.

Static analysis

No suspicious patterns detected.