Back to skill

Security audit

Digistore24

Security checks for vulnerabilities and agentic risk

Overview

The data-reading functions fit the stated purpose, but setup can execute unchecked downloaded code and introduce additional agent skills without clear user control.

Review and install a verified CLI release yourself before allowing setup. Consider the buyer and purchase data available through your connected account. To prevent additional agent skills from being installed automatically, upstream documents OO_SKILLS_SYNC_DISABLED=1. The remote installers and hosted connector implementation remain unverified; no bundled malicious payload was found.

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 performs remote installer execution, not the declared Digistore24 data access. Although installation can support a skill, nothing in this chunk establishes that the Oomol installer is a required Digistore24 dependency. The downloaded script's further behavior is not visible and cannot be determined from this code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command executes the current contents of a remote installation script immediately, without pinning or independently verifying the downloaded artifact. HTTPS protects transport but does not protect against a compromised publisher or hosting endpoint, which could supply code capable of accessing local files and credentials with the user's privileges.

Content

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

The setup workflow executes downloaded installation scripts without warning about system-integrity risks.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions pipe remote content directly into Bash or PowerShell without an integrity-verification step or explicit installation approval. If the installation endpoint or delivery infrastructure is compromised, an otherwise read-only data request could lead to arbitrary code execution with the invoking user's privileges; the missing-CLI condition limits exposure but does not prevent exploitation.

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