ClawHub
Back to skill

Security audit

Doc Miner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward document-analysis helper that discloses sending provided documents or URLs to an external AI service.

Install only if you are comfortable sending the documents, pasted text, or URL contents you provide to aiprox.dev/LightningProx for Claude-based processing. Avoid confidential or regulated documents unless the provider's retention and access terms meet your requirements.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill extracts data from "any URL, PDF, or raw text" and "Auto-detects mode from task," but it does not define a narrow trigger scope or clear boundaries for when this skill should activate instead of other general-purpose document or summarization skills. Because this is a manifest/markdown file, such broad invocation language can cause unintended matches with ordinary user requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L29 states that "asking a question triggers Q&A mode" and '"extract" triggers extraction mode,' which are common patterns in everyday speech and are not scoped to a narrow command context. The file does not provide explicit exclusions or a complete trigger list, making invocation behavior ambiguous.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The skill sends user-provided document text or URL-derived content to an external service at aiprox.dev and authenticates using an environment token. This creates a real data-transmission boundary: sensitive document contents may leave the local trust domain, and URLs may cause remote fetching of internal or private resources if not tightly constrained by the backend.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

Make Request

bash
curl -X POST https://aiprox.dev/api/orchestrate \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $AIPROX_SPEND_TOKEN" \
  -d '{