Back to skill

Security audit

AssemblyAI

Security checks for vulnerabilities and agentic risk

Overview

The AssemblyAI actions have clear safeguards, but fallback setup executes unverified remote code without a separate approval step.

Review and approve CLI installation separately before letting an agent perform setup. Check the installer's integrity and the CLI's bundled-skill behavior. OOMOL will mediate access to your connected AssemblyAI account; creation and deletion remain subject to explicit confirmation. The complete bundled artifact was inspected, but remote installer contents and external credential handling 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied code performs remote script execution for an Oomol CLI installer. It contains no AssemblyAI interaction or evidence establishing this installation as a supporting dependency for AssemblyAI tasks. The remote script's contents are not supplied, so its subsequent behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command executes mutable remote content immediately, without a pinned version, signature check, or opportunity to review the downloaded script. Compromise of the vendor's distribution infrastructure could therefore compromise the local account; this is the same underlying installation risk identified by SQP-2, not a separate attack chain.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Fallback setup executes remotely downloaded installation scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback setup directs execution of remotely downloaded shell and PowerShell scripts without integrity verification or explicit approval for local installation. A compromised distribution endpoint could execute arbitrary code with the invoking user's privileges; the missing-CLI condition limits exposure but does not make execution safe.

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 81)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