Back to skill

Security audit

TPSCheck

Security checks for vulnerabilities and agentic risk

Overview

The phone-checking functions fit the purpose, but setup can execute unchecked downloaded code and introduce persistent agent skills without clearly explaining those changes.

Review and approve the CLI installation separately before allowing automatic setup. Its documented defaults can install additional agent skills; consider disabling startup synchronization with OO_SKILLS_SYNC_DISABLED=1. Submit only phone numbers you intend to share through OOMOL with TPSCheck. The bundled instructions were fully inspected, but the external installers and hosted connector 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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied command performs remote code execution for an installer, with no visible TPSCheck query or data-reading behavior. Although installing a dependency can be a supporting implementation detail, the supplied content does not establish that this installer supports TPSCheck. 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
90% confidence
Finding

The supplied chunk performs only a CLI login, rather than the declared TPSCheck search/read behavior. Authentication could be a supporting implementation detail if the CLI were established as a TPSCheck dependency, but the supplied content provides no such connection. The command alone does not establish which service is accessed or how credentials are handled.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping an HTTPS download directly into bash executes whatever script the endpoint currently returns with the invoking user's permissions, without a pinned version or independent integrity check. A compromised distribution endpoint could therefore cause arbitrary code execution; this is the same underlying installation risk identified in the setup-workflow finding, not an independent exploit chain.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

The action workflow lacks a privacy warning about transmitting phone numbers through OOMOL to TPSCheck.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to submit action payloads, which for the phone-check actions contain user-supplied phone numbers. Although the connector is identified, the skill does not warn that these potentially personal identifiers are transmitted through OOMOL to a third-party service; labeling untagged actions safe to run directly does not address that privacy impact.

Content

No source excerpt is available for this finding.

The setup workflow executes downloaded installation scripts without warning about their system impact.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

On a missing-CLI error, the setup instructions direct execution of downloaded shell or PowerShell code without an explicit installation approval or integrity-verification step. This can modify the host and expose files or credentials if the distribution endpoint or installer is compromised; the conditional setup trigger limits frequency but does not make the 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 78)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