ClawHub
Back to skill

Security audit

agente-investigadora-f100k

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed content-research workflow that uses social/media research tools to produce a brief, with no bundled code or hidden persistence.

Before installing, confirm you are comfortable with the skill sending handles, social metrics, niche details, competitor information, and screenshots or connected-account data to the named research services and Telegram. Use it for explicit content-research briefs, and confirm costs before Apify-heavy runs.

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
Confidence
96% confidence
Finding
The skill explicitly orchestrates external services (Apify, Composio, web search) and may process account handles, niche data, and potentially business-sensitive performance information, but it does not clearly warn the user that this data will be sent to third-party services. In context, this omission is more dangerous because the workflow includes analysis of the user’s own account and metrics, which can expose sensitive operational data without informed consent.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation examples are broad enough that the skill may run on ordinary research requests without first confirming scope, platform, target account ownership, or whether external tools should be used. In this skill’s context, unintended activation can cause over-collection and transmission of niche, competitor, or account data to Apify/Composio/web services, creating privacy, cost, and least-privilege issues even if no explicitly malicious action is intended.

Static analysis

No suspicious patterns detected.