ClawHub
Back to skill

Security audit

AWS STS

Security checks across malware telemetry and agentic risk

Overview

This AWS STS skill is not malicious, but it under-discloses that its main actions can issue temporary AWS credentials and tells agents they are safe to run directly.

Review this skill before installing. Only use it when you intentionally want an agent to call AWS STS through OOMOL, and require explicit approval before `assume_role` or `get_federated_credentials` so temporary credentials are not produced unintentionally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The manifest claims the skill is for 'searching and reading data,' but the documented actions issue temporary AWS credentials via AssumeRole and federated credential flows. This misclassification can cause an agent or user to treat credential-minting operations as low-risk read activity, increasing the chance of unauthorized privilege use or accidental secret exposure.

Intent-Code Divergence

High
Confidence
98% confidence
Finding
The safety section states untagged actions are reads, but the only listed untagged actions return temporary credentials rather than passive read-only data. Treating credential issuance as a safe read operation is dangerous because it can authorize further AWS actions outside the immediate skill and bypass expected approval boundaries.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger text says to use this skill for ANY AWS STS request, which is overly broad and may cause automatic invocation whenever STS is merely mentioned. In the context of a skill that can mint temporary credentials, broad routing increases the likelihood of unintended execution of sensitive operations.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.