Back to skill

Security audit

Papertrail

Security checks for vulnerabilities and agentic risk

Overview

Papertrail operations have clear approval safeguards, but automatic setup runs unverified remote code and omits broader changes to installed agent skills.

Review setup before installing. Install a reviewed CLI version yourself and consider setting OO_SKILLS_SYNC_DISABLED=1 before invoking it to prevent automatic changes to other agent skills. Confirm that OOMOL may process your Papertrail data, and retain the skill's approval requirements for changes and deletions. The remote installer and hosted connector implementation remain unverified. [Synchronization control](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md)

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 installs or runs software from an Oomol-hosted endpoint rather than performing the declared Papertrail operations. Although dependency installation can be a supporting implementation detail, the supplied chunk establishes no relationship between this installer and Papertrail. The downloaded script is not provided, so its further 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 installation command streams a mutable third-party script directly into Bash without independent integrity verification or inspection; the PowerShell alternative has the same weakness. If the distribution endpoint or supply chain is compromised, the script can execute arbitrary commands with the agent process's privileges and access local files or credentials. Its legitimate dependency-setup purpose and missing-command prerequisite reduce exposure but do not remove the risk.

Content

Scanner excerpt · SKILL.md (reported line 61)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 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