Back to skill

Security audit

Toggl Track

Security checks for vulnerabilities and agentic risk

Overview

The Toggl workflow is coherent, but missing software can trigger an unverified remote installer without user approval.

Review and approve CLI installation separately before using this skill, including any changes to other agent skills. Understand that Toggl access goes through OOMOL, and retain the required confirmations for writes and deletions. The bundled instructions were fully inspected, but remote installer contents and backend behavior 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
93% confidence
Finding

The supplied chunk performs an external CLI installation rather than Toggl Track operations. Although installation can be a supporting implementation detail, nothing supplied establishes this installer's relationship to Toggl Track or its necessity for the declared functionality. The downloaded script's contents and further effects 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 a remotely fetched, mutable script directly into Bash executes its contents without a separate integrity-verification or review step. If the distribution endpoint or publishing pipeline is compromised, an attacker could execute code with the agent's local privileges, potentially accessing files and credentials; the Windows installer uses an equivalent download-and-execute pattern.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

Fallback setup executes remote installation scripts without warning the user about system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs the agent to install software after a command-not-found error without requiring informed user approval for local system changes. Confirmation requirements elsewhere cover Toggl mutations, not installation, so a request to manage time entries could unexpectedly trigger execution of an installer with the agent's local privileges.

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 99)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