Back to skill

Security audit

Listen Notes

Security checks for vulnerabilities and agentic risk

Overview

The podcast search workflow fits its purpose, but setup can execute downloaded software without a clear user approval step.

Review the setup behavior before enabling this skill. Install a reviewed CLI version yourself and require approval before any downloaded installer runs. Consider OOMOL account access, usage charges, and the CLI's automatic skill synchronization. The bundled search workflow is coherent, but the external installer and runtime implementation remain unverified; the empty static-scan result does not resolve those concerns.

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 fallback instructions expand a search/read task into local software installation without requiring explicit user approval. Accessing the connector vendor's domain is relevant to setup, not inherently suspicious, but executing its downloaded installer introduces local code-execution risk beyond the advertised task. This overlaps with the installation findings below rather than representing a separate exploit.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied chunk performs only an authentication login operation; it contains no Listen Notes search or data-reading behavior. Authentication could support the declared purpose, but nothing in this chunk establishes that oo authenticates to Listen Notes. As supplied, the demonstrated behavior does not match the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a remotely fetched, mutable script directly into Bash without a pinned version or independent integrity verification; the PowerShell alternative has the same issue. If the distribution endpoint or release pipeline is compromised, attacker-controlled code could run with the invoking user's permissions. HTTPS and the missing-CLI prerequisite reduce some exposure but do not establish the script's integrity.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

The setup workflow directs the agent to execute downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

A missing-command error triggers instructions to install software without explaining local changes or asking for approval. Requesting podcast data does not itself authorize modifying the local environment. The declared tool restriction may prevent these commands from running, but the skill should not rely on that restriction instead of an explicit installation boundary.

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 84)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