The SignalHire skill integrates the full SignalHire API into OpenClaw, enabling you to search for prospects and enrich their contact details without leaving your workflow. It exposes three core actions: a credits check, a search-by-query for prospecting, and an asynchronous contact enrichment call

• Outcome: Review
• Latest audit: Sep 18, 2026 · 8:51 PM UTC
• Version: 1.0.1

Overview

The skill is a coherent SignalHire integration, but it handles personal contact data and webhook callbacks with insufficient privacy, storage, and execution safeguards.

Review this skill carefully before installing. Only use it with a legitimate SignalHire account and a lawful basis for looking up personal contact data, avoid unnecessary storage or sharing of results, and prefer a presecured callback service over having the agent deploy or manage a public webhook receiver. If shell commands are used, keep API keys and callback secrets out of logs and command history where possible.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The skill is designed to retrieve emails, phone numbers, and social profile data about individuals, but it does not instruct the agent to warn users that this is privacy-sensitive personal data or to verify appropriate authorization and lawful use. In context, this omission is significant because the skill operationalizes contact enrichment and lead generation, which raises elevated privacy, compliance, and misuse risks.

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The skill instructs the agent to deploy and operate a publicly reachable webhook receiver and persist callback data to disk, which materially expands capability beyond a simple third-party API integration. This creates additional attack surface including unsolicited inbound requests, secret leakage in URLs, insecure local data handling, and misuse of the agent as a network service host.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The callback workflow directs saving enriched personal data to a known local file without any user-facing notice about local retention, file protection, or cleanup. Because the data includes potentially sensitive contact details, writing it to disk increases exposure through accidental disclosure, over-retention, or access by other local processes.

Context-Inappropriate Capability

Medium

• Confidence: 89% confidence
• Finding: The skill explicitly directs use of the exec tool to run curl or fetch scripts, granting shell/script execution where a constrained HTTP client would be sufficient. This needlessly broadens execution privileges and increases the chance of command injection, secret exposure in process arguments, or unintended system interaction if parameters are influenced by user input.

Static analysis

No suspicious patterns detected.