ClawHub
Back to skill

Security audit

Picrd Image Hosting

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for uploading user-chosen images to picrd.com, with disclosure that hosted images are externally accessible.

Install only if you intentionally want agents to upload non-sensitive images to picrd.com. Treat unlisted links as shareable, not private, and keep the delete URL if you may need to remove an upload later.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is heavily keyword-stuffed with broad terms like 'free hosting', 'file hosting', and 'file share', which can cause the skill to trigger on generic user requests unrelated to deliberate image-upload intent. In an agent setting, overbroad routing is dangerous because it increases the chance that users’ files or screenshots are sent to a third-party public hosting service when they only asked for help sharing, storing, or handling files in general.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s primary usage flow encourages uploading screenshots, diagrams, and generated images to a public third-party service without a prominent warning immediately before transmission. Because screenshots and images frequently contain secrets, personal data, internal documents, or tokens, this omission can lead to unintended disclosure of sensitive information to a permanent externally hosted URL.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.