Back to skill

Security audit

Dovetail

Security checks for vulnerabilities and agentic risk

Overview

The Dovetail workflow is coherent, but its fallback setup directs the agent to execute an unverified online installer without separate user approval.

Review and explicitly approve a verified CLI installation before allowing fallback setup. OOMOL mediates access to your connected Dovetail account, and writes require confirmation. The remote installers could not be inspected, so their local changes remain unverified; upstream documentation also describes installing additional agent skills.

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 code performs remote software installation rather than the declared Dovetail operations. Installing a supporting dependency could be legitimate, but the supplied material establishes no connection between this Oomol installer and Dovetail. The downloaded script is not included, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote installer directly into bash executes its contents without prior inspection or independent integrity verification. HTTPS protects transport but does not protect against compromise of the installer host or publishing pipeline, which could allow code execution and access to files or credentials available to the agent; the legitimate setup purpose and conditional trigger reduce exposure but do not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Fallback setup executes downloaded installer scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback instructs the agent to execute downloaded shell or PowerShell code without an explicit installation approval step or integrity verification. Although limited to a missing-CLI condition, installation can change the local system and execute with the agent's privileges, exceeding the user's ordinary authorization to operate Dovetail.

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 82)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