ClawHub
Back to skill

Security audit

Lensmor Exhibitor Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Lensmor API integration for finding trade-show exhibitors, with expected external data sharing but no hidden execution, persistence, or credential exposure found.

Install this only if you are comfortable sending company URLs, target-audience descriptions, event IDs, and related prospecting context to Lensmor. Keep LENSMOR_API_KEY in the environment or a secrets manager, not in prompts or shared documents, and review Lensmor's data-handling terms for confidential prospecting workflows.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 170)May include surrounding context.

md
| "is this show worth it?" | Run `lensmor-event-fit-score` first |
| "show me more" / "next page" | Re-call with `page` incremented by 1 |

## Output Rules

1. All URLs formatted as `[text](url)` — never bare links
2. Never output the value of `LENSMOR_API_KEY`

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · examples/saas-vendor-at-dreamforce.md (reported line 16)May include surrounding context.

API Call

bash
curl -X POST https://platform.lensmor.com/external/exhibitors/search \
  -H "Authorization: Bearer uak_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 37)May include surrounding context.

md
- Lensmor API key (`uak_your_api_key`) — contact [hello@lensmor.com](mailto:hello@lensmor.com) to purchase
- Base URL: `https://platform.lensmor.com`
- Full API docs: [https://api.lensmor.com/](https://api.lensmor.com/)

## Install

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata and description contain many broad, multilingual trigger-style phrases such as 'who is exhibiting at this show' and 'find exhibitors', which are common user utterances and may cause the skill to activate in contexts the user did not explicitly intend. Unintended invocation can disclose business queries to the external Lensmor API or steer the conversation into data collection and external calls without sufficiently clear user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example explicitly sends a user-supplied company URL and an API key to a third-party endpoint, but the surrounding documentation does not warn that organizational profiling data will be transmitted externally. In a skill context, this can lead users or downstream agents to share sensitive business-identifying inputs without informed consent or review, creating privacy, confidentiality, and procurement-risk concerns.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

This example demonstrates outbound transmission to an external API using a bearer token and includes company profiling input in the request body. While expected for an API integration, it is still a genuine security concern in an agent skill because it normalizes sending potentially sensitive business context to a remote service and may encourage unsafe reuse of real credentials in prompts, logs, or copied examples.

Content

Scanner excerpt · examples/saas-vendor-at-dreamforce.md (reported line 16)May include surrounding context.

API Call

bash
curl -X POST https://platform.lensmor.com/external/exhibitors/search \
  -H "Authorization: Bearer uak_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The workflow says 'When this skill triggers' and immediately instructs data collection and API-key checks, but it does not define exact trigger boundaries or exclusions. This ambiguity increases the chance of accidental activation and unnecessary handling of potentially sensitive company URLs or target-audience data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.