Back to skill

Security audit

AWS STS

Security checks for vulnerabilities and agentic risk

Overview

Review before installing: the AWS workflow fits its purpose, but setup executes unverified remote code and leaves persistent changes to agent skills undisclosed.

Review and approve CLI setup separately using a trusted, version-pinned distribution. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; configure it before invoking the CLI if those changes are unwanted. Connect only the AWS permissions you need and treat returned temporary credentials as secrets. The remote installers and service implementation remain unverified.

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
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code performs remote software installation, not AWS STS operations. Although installation can be a supporting implementation detail, the chunk provides no evidence that this installer supports the declared STS purpose. The contents and further effects of the remote script are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The only supplied behavior is a CLI login command, with no visible connection to AWS STS. Although authentication can be a supporting implementation detail, this chunk provides no evidence that the login supports the declared AWS STS functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping the HTTPS response directly into Bash executes mutable remote content without verifying a pinned version or independently trusted signature. If the installer host or publication pipeline is compromised, attacker-controlled code could access files and credentials available to the agent; HTTPS alone does not address that supply-chain threat.

Content

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

Fallback setup executes remote installation scripts without warning about the system-integrity risk.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback instructs the agent to execute remotely supplied shell or PowerShell code without a documented integrity check or explicit installation approval. A compromised installer distribution path could execute arbitrary code with the agent process's permissions; the missing-CLI condition limits exposure but does not protect an affected execution.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 77)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources