ClawHub
Back to skill

Security audit

Picky Assist

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Picky Assist connector skill, but users should review the one-time CLI install command and confirm any message-sending action before use.

Install this only if you want an agent to use your connected OOMOL/Picky Assist account. Review the oo CLI installer before running it, and require clear confirmation of recipients, message content, and expected effect before any send_messages action.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill instructs running a remote installation script via curl ... | bash, which executes code fetched at runtime without integrity verification, pinning, or manual review. Because the skill content is untrusted and the command is presented as a remediation step, this creates a supply-chain and arbitrary code execution risk if the remote host, network path, or script content is compromised.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger guidance is overly broad: 'Use this skill for ANY Picky Assist request' and 'Whenever a task involves Picky Assist, use this skill instead of calling the API directly' can cause the agent to invoke this skill for any mention of Picky Assist, even when the user did not explicitly ask to act on their account. In a skill that can perform writes (send_messages), this increases the risk of unintended account access or accidental state-changing operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.