ClawHub
Back to skill

Security audit

Prediction Bridge Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward live prediction-market data client that discloses its networked API use and does not show hidden persistence, credential access, destructive actions, or unrelated behavior.

Install this if you want agents to fetch live prediction-market data from Prediction Bridge. Be aware that search terms, market IDs, and wallet addresses you ask about may be sent to the configured API endpoint, and only override PREDICTION_BRIDGE_URL with a service you trust.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill invokes a bundled Python script that uses network access and can read environment configuration, but the manifest does not declare any tool scope or allowed-tools restrictions. This creates an unclear trust boundary: an agent may activate the skill without explicit disclosure that it will execute code with network capability, increasing the chance of unintended outbound requests or access to sensitive environment-derived configuration.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description contains broad activation language such as using the skill whenever a user asks about prediction markets, odds, prices, analytics, or related news, which can match many ordinary finance or current-events queries. Over-broad triggering increases the likelihood that the agent will run the bundled script and make live network requests in situations where the user did not clearly ask for external data access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.