Back to skill

Security audit

Harvest

Security checks for vulnerabilities and agentic risk

Overview

Harvest changes require approval, but automatic setup executes unverified downloaded code without a separate approval step.

Review the setup before installing. Independently obtain and verify the CLI, check its automatic changes to installed agent skills, and limit the connected Harvest account's permissions. OOMOL mediates Harvest access and credentials. The downloaded installers and hosted implementation remain unverified; no malicious behavior was established in the bundled artifact.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command executes an Oomol installer rather than interacting with Harvest. Dependency installation can be a supporting implementation detail, but the provided content does not establish that this installer supports Harvest functionality. The remote script's contents are not supplied, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The setup instructions pipe a remotely retrieved, unpinned script directly into Bash, with an equivalent download-and-execute pattern for PowerShell. Compromise of the distribution endpoint or installer could execute arbitrary code with the invoking user's privileges, exposing local files and credentials. The missing-CLI prerequisite limits when this occurs, and the declared tool allowlist may block installation if enforced, but neither makes the installation instructions themselves safe.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

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 90)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