ClawHub
Back to skill

Security audit

linkdigest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent social-link reading helper, with privacy considerations because links and fetched media are processed by an external digest service.

Install only if you are comfortable having supported social links and their fetched media processed by the linkdigest service. Avoid using it for private, sensitive, access-token-bearing, or confidential links unless the user explicitly intends that processing.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill describes sending links to a service that fetches media, transcribes audio, performs OCR, and describes images, but it does not warn that this involves transmitting third-party URLs and potentially sensitive content to an external processor. Users may unknowingly cause personal, private, or copyrighted content to be analyzed off-platform without informed consent, creating privacy and compliance concerns.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to invoke the external tool whenever a user pastes a supported social-media URL, even if the user provides no explicit request beyond the link. That broad activation rule can cause unconsented transmission of third-party URLs and linked content to an external service, increasing privacy and data-handling risk and making overuse or unnecessary invocation more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.