Back to skill

Security audit

Diffy

Security checks for vulnerabilities and agentic risk

Overview

The Diffy features are coherent, but a missing dependency can trigger execution of an unverified online installer without explicit user approval.

Review the setup behavior before installing. Install a verified oo CLI separately, or require approval before any downloaded installer runs. Connecting Diffy gives OOMOL access to the connected account; use an appropriately scoped account. The complete bundled artifact was reviewed, but external installer and service behavior remain unverified.

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
99% confidence
Finding

The supplied command runs an external installer and contains no Diffy search or read operation. Nothing in the provided chunk establishes that this installation supports Diffy, so it is not justified as a supporting implementation detail. The installer's contents and downstream effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The supplied chunk performs a CLI login rather than searching or reading Diffy data. Authentication could be a supporting implementation detail, but nothing in this chunk connects oo authentication to Diffy or implements the declared functionality. This assessment is limited to the supplied code.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a remotely fetched, unpinned script directly into Bash, allowing the response to execute with the agent's local privileges without integrity verification or prior inspection. HTTPS provides transport protection but does not protect against a compromised publisher or distribution endpoint; the PowerShell fallback has the same execution pattern.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Fallback setup executes remote installation scripts without warning the user about the system-integrity implications.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The missing-CLI fallback directs the agent to execute downloaded installation code without explicitly requiring user approval or explaining that this can modify the local system. Although conditional setup reduces exposure, a routine Diffy read request could lead to code execution with the agent's operating-system privileges; this overlaps with SC2 rather than representing a separate execution path.

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 81)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