Back to skill

Security audit

Slite

Security checks for vulnerabilities and agentic risk

Overview

Slite operations have clear approval safeguards, but setup executes downloaded code and may make broader agent changes without clear user control.

Review and approve CLI installation separately, use a verified release, and disable automatic skill synchronization if you only want Slite access. OOMOL processes the connector requests and manages the Slite credential. Keep the documented approval requirements for writes and deletions. The remote installer and runtime were not verified in this review.

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
97% confidence
Finding

The supplied chunk runs an Oomol installer rather than performing Slite operations. Nothing in the chunk establishes that this installation supports the declared Slite functionality. The downloaded script's contents are not supplied, so its further effects cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command executes mutable remote content with the agent process's local privileges, without a pinned version or independent integrity verification. Compromise of the installer distribution could allow credential theft or local file modification; HTTPS and the domain's legitimate connection to the workflow reduce suspicion of malicious intent but do not eliminate this supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback directs the agent to install software by immediately executing downloaded shell or PowerShell code, without explicitly obtaining approval for local installation. Although installation supports the legitimate connector workflow and occurs only when the CLI is missing, a Slite request does not necessarily authorize arbitrary local code execution or system changes.

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 83)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