Back to skill

Security audit

Riveter

Security checks for vulnerabilities and agentic risk

Overview

The Riveter integration is coherent, but its automatic setup can execute unverified installers and introduce broader agent changes without clearly explaining them.

Review and approve the CLI installation separately before enabling automatic setup. Prefer a verified, fixed release, and consider disabling managed-skill synchronization using the documented OO_SKILLS_SYNC_DISABLED control. OOMOL brokers the connection and requests, and scraping may consume credits. The installer payload and hosted implementation were not verified; no malicious behavior was established.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs remote script execution from an Oomol endpoint. Nothing in the supplied code connects that installation to Riveter or implements the declared search/read functionality, so this is not established as a supporting implementation detail. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping an HTTPS response directly into Bash executes whatever the endpoint supplies without pinning or verifying the installer. A compromised installer or distribution service could access local files and credentials or modify the environment; the missing-CLI condition reduces exposure but does not protect execution integrity.

Content

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

The setup workflow executes downloaded installation scripts without warning about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions direct execution of downloaded shell and PowerShell scripts without an explicit approval checkpoint or artifact verification. Although restricted to a missing-CLI fallback, this can turn a read-oriented task into arbitrary code execution with the agent process's permissions if the distribution endpoint or installer is compromised.

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