ClawHub
Back to skill

Security audit

ipo-tracker

Security checks for vulnerabilities and agentic risk

Overview

This IPO-tracking skill is purpose-aligned and does not show malicious behavior, but it is incomplete and should better disclose dependency installation and file creation.

Install only if you are comfortable with a skill that may run Python commands, install dependencies, fetch market data from external services, and write IPO report/watchlist files. Confirm the actual script and dependency files before running it, because they are not included in this inspected artifact.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises broad natural-language trigger phrases, increasing the chance it activates on loosely related user requests and runs tool-assisted actions unexpectedly. In this skill, unintended activation could lead to dependency installation, script execution, network access for scraping/data retrieval, and creation of output files without the user clearly requesting those side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The execution instructions include installing Python dependencies and generating multiple local files, but the skill description and response guidance do not prominently warn about these side effects. This can mislead users or orchestrators into approving execution without understanding that code will be installed and run, remote packages may be fetched, and artifacts will be written to disk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.