ClawHub
Back to skill

Security audit

Prediction Bridge Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently searches prediction markets through Prediction Bridge's backend, with the main caution that user text or URLs are sent to that external service.

Install only if you are comfortable with search queries, article URLs, or X/Twitter links being sent to Prediction Bridge's backend. Do not use it with secrets, private/internal links, personal data, or confidential business text unless you trust that service's handling of the data.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly directs the agent to send user-provided text or X/Twitter URLs to a remote backend, but it does not require disclosure or confirmation that the content will leave the local agent environment. This creates a real privacy and data-handling risk, especially if users paste sensitive text, private links, or proprietary material expecting local-only processing.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
API_URL="${PREDICTION_BRIDGE_API_URL:-https://prediction-bridge.onrender.com/api/v1}"

curl -sS -X POST "$API_URL/search/unified" \
  -H "Content-Type: application/json" \
  -H "X-Request-ID: pb-$(date +%s)" \
  --data-binary @- <<'JSON'
Confidence
96% confidence
Finding
The documented curl command performs external transmission of raw user input to a third-party API endpoint. While this is core functionality rather than obviously malicious behavior, it is still a genuine security concern because any sensitive text or URLs supplied by the user are exfiltrated off-system without embedded safeguards, consent flow, or data-classification checks.

Static analysis

No suspicious patterns detected.