ClawHub
Back to skill

Security audit

Lensmor Recommendations

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Lensmor API integration for ranking trade-show exhibitors, with expected external API use and no evidence of hidden execution, persistence, or destructive behavior.

Install this only if you intend to use Lensmor's hosted API and are comfortable sending trade-show targeting details, ICP criteria, company profile information, and account shortlists to that service. Do not include confidential, regulated, or highly sensitive sales strategy data unless your organization has approved Lensmor for that use.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

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 194)May include surrounding context.

md
| `lensmor-recommendations` | `event_id` + optional filters | AI-driven ICP ranking for a specific event |
| `lensmor-exhibitor-search` | `company_url` or `target_audience` | Profile-based search across all events or a specific event |

## Output Rules

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

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 49)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
93% confidence
Finding

The description embeds many broad multilingual example phrases that could cause the skill to activate on generic user requests without a tightly defined boundary. Over-broad activation can route unrelated conversations into this skill, leading to unintended API use, confusing responses, or incorrect delegation in a multi-skill environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'When this skill triggers' section describes post-activation workflow steps but does not specify the actual condition for invocation. In an orchestrated agent system, ambiguous trigger semantics increase the chance of misrouting, which may expose user context to the wrong skill or cause unnecessary external API calls.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README states that the agent sends company profile and targeting criteria to Lensmor's external matching API, but it does not clearly warn users that potentially sensitive sales strategy data will leave the local environment. This creates a privacy and data-governance risk because users may disclose proprietary ICP details, account lists, or go-to-market plans without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.