Back to skill

Security audit

Drimify

Security checks for vulnerabilities and agentic risk

Overview

The Drimify reads match the stated purpose, but its helper can install persistent skills into other agents without the skill explaining those broader changes.

Review the helper's persistent changes before allowing setup. Use a separately verified CLI installation and disable startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1 if additional agent skills are unwanted. OOMOL mediates the Drimify connection. The installer contents and deployed connector implementation were not verified; the bundled-file coverage exceptions were resolved by direct inspection.

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
99% confidence
Finding

The supplied command performs remote script execution rather than searching or reading Drimify data. Nothing in the chunk establishes that installing the Oomol CLI is a supporting dependency for Drimify access. The script's downstream actions are not visible, but downloading and executing this unrelated installer is itself outside the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping the HTTPS response directly into Bash executes mutable remote content without prior inspection or artifact verification. HTTPS protects transport but does not prevent a compromised publisher or distribution endpoint from supplying malicious code; this is the same underlying installer risk identified by SQP-2, not an independent exploit.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Setup instructions execute remote installer scripts without a system-integrity warning.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup instructions execute downloaded shell or PowerShell code immediately, without an explicit installation approval step or artifact-integrity verification. A compromised installer source could execute arbitrary code with the invoking user's privileges; restricting setup to a missing-CLI error reduces exposure but does not remove this risk.

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 77)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