Back to skill

Security audit

Sorftime

Security checks for vulnerabilities and agentic risk

Overview

The Sorftime integration fits its purpose, but its setup instructions can execute unverified downloaded code without asking you first.

Require separate approval for CLI installation and prefer a pinned, verified release. Check whether the CLI will install or synchronize other agent skills. OOMOL mediates the Sorftime connection, and queries consume the listed service credits. The remote installers and hosted connector implementation remain outside the inspected package; the Review verdict concerns setup control, not evidence of malicious behavior.

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
96% confidence
Finding

The declared purpose concerns Sorftime data access, but the supplied chunk runs an external installer. Nothing provided establishes this installation as a supporting dependency for Sorftime functionality. The remote script's contents are unavailable, so its downstream actions cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The only supplied action is authentication, rather than the declared Sorftime data operations. Authentication could be a legitimate supporting detail if oo were established as a Sorftime client, but the supplied content provides no such connection. The assessment is limited to this chunk; the CLI's target service cannot be determined from the command alone.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable HTTPS download directly into bash executes remote code without an independent integrity check or review; the PowerShell alternative has the same weakness. If the distribution endpoint or release pipeline is compromised, the installer could access local files, steal credentials, or modify the environment with the invoking user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning about remote-code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

On a missing-CLI error, the workflow directs installation by executing a remote script without requiring explicit approval for local code execution and system changes. Although this is a legitimate setup dependency rather than evidence of malicious intent, it expands a read-oriented task into execution with the invoking user's 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 108)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