ClawHub
Back to skill

Security audit

Pilt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Pilt API helper that uses the user's Pilt API key to fetch fundraising-related data from Pilt.

Install only if you intend to connect your agent to your Pilt account. Confirm that OpenClaw securely maps the configured apiKey to PILT_API_KEY, and treat the Pilt API key like any other account secret.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
Returns matched investors with fit scores from the user's latest deck analysis.

```bash
curl -s -X POST \
  https://pilt.ai/api/v1/gateway \
  -H "Content-Type: application/json" \
  -H "x-pilt-api-key: $PILT_API_KEY" \
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Intent-Code Divergence

Low
Confidence
97% confidence
Finding
At L094 the documentation says the key should be available as the `PILT_API_KEY` environment variable, but the provided OpenClaw example at L100-L103 stores it as `apiKey` instead of showing an environment-variable mapping. This is an active documentation contradiction about how authentication is supplied, not just an omitted detail.

Static analysis

No suspicious patterns detected.