Back to skill

Security audit

Paperform

Security checks for vulnerabilities and agentic risk

Overview

The Paperform reads match the advertised purpose, but setup can execute downloaded software without clear user approval.

Review the setup before installing. Prefer a separately reviewed, version-pinned CLI installation and require approval before running downloaded installers. Consider disabling automatic skill synchronization using the documented OO_SKILLS_SYNC_DISABLED setting. OOMOL mediates access to your Paperform data; external installer behavior remains unverified. No malicious behavior was established.

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
96% confidence
Finding

The supplied command performs remote software installation rather than searching or reading Paperform data. Although dependency installation can be a supporting implementation detail, this chunk establishes no relationship between the Oomol installer and the declared Paperform functionality. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a remotely fetched script directly into bash executes whatever the endpoint returns with the invoking user's privileges, without a pinned version or independent integrity verification. Compromise of the installer distribution path could therefore expose local files and credentials or enable persistent system changes; the legitimate dependency and conditional setup trigger reduce exposure but do not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback instructs an agent to execute downloaded installation scripts without first explaining that this runs external code and can modify the local environment. Although restricted to a missing-CLI error, installation is a materially different operation from reading Paperform data and warrants separate user authorization.

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 89)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