ClawHub
Back to skill

Security audit

AWS S3

Security checks for vulnerabilities and agentic risk

Overview

This S3 skill is coherent, but it needs review because it can affect AWS S3 data and its setup/safety instructions are under-scoped.

Install only if you trust OOMOL and are comfortable granting the connected AWS credential's S3 permissions through this connector. Before use, require explicit approval for uploads, deletes, overwrites, and presigned URLs that allow upload or delete, and avoid running the remote installer unless you have independently verified the source or use a safer installation method.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software via curl ... | bash, which executes a remote script without verification. In a security-sensitive automation context, this creates a direct supply-chain and arbitrary code execution risk if the host, network path, or distribution endpoint is compromised.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY AWS S3 request" and "Whenever a task involves AWS S3, use this skill," which is extremely broad and lacks scope boundaries or exclusion conditions. In a markdown/manifest context, this can overlap with many routine mentions of S3 and does not clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The safety section incorrectly classifies all untagged actions as read-only, but generate_presigned_url can mint upload or delete-capable URLs that enable indirect modification or deletion of S3 objects. This can mislead an agent into treating a mutating capability as safe, reducing confirmation requirements for actions that materially change state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.