Back to skill

Security audit

NewsCatcher

Security checks for vulnerabilities and agentic risk

Overview

The news features fit their purpose, but setup directs the agent to execute unverified downloaded code without a clear approval step.

Review setup before installing. Prefer a verified, pinned CLI installation and require approval before downloaded installers run. Review its bundled-skill changes; the publisher documents OO_SKILLS_SYNC_DISABLED=1 to disable startup synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md). NewsCatcher access is routed through your OOMOL-connected account and may consume credits. No bundled malicious payload was found, but the external installer and runtime were not verified.

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
99% confidence
Finding

The supplied command executes an external installation script and contains no NewsCatcher search or data-reading operation. Nothing provided establishes this installer as a supporting dependency for NewsCatcher, so its execution is an undeclared capability involving an inconsistent resource. The downloaded script's further behavior cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

Authentication can be a supporting implementation detail, but the supplied chunk contains only a login command and provides no connection to NewsCatcher. Its observable purpose therefore differs materially from the declared NewsCatcher functionality. The command alone does not establish which service is authenticated or whether credentials are stored.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into bash without a pinned version or independent integrity verification; the PowerShell alternative has the same trust problem. Compromise of the installer endpoint or its distribution infrastructure could execute attacker-controlled code with the invoking user's permissions, although exposure is limited to the missing-CLI setup path.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes remote installation scripts without warning the user about local code execution and system changes.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

A missing CLI triggers instructions to execute downloaded installation code without first explaining the local changes or obtaining explicit installation approval. Although conditional setup reduces exposure, a news-reading request does not itself authorize arbitrary local code execution, which can modify files and access data with the invoking user's permissions.

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 79)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