Back to skill

Security audit

Docsumo

Security checks for vulnerabilities and agentic risk

Overview

The Docsumo workflow is clearly scoped, but setup can execute downloaded software and introduce additional agent instructions without separate approval.

Review the setup before installing. Install a reviewed, version-pinned CLI yourself and disable automatic skill synchronization if you want only this Docsumo integration. Connect an account whose document data you intend the agent and OOMOL to access, and confirm uploads. The downloaded installers and hosted implementation remain unverified; the artifacts do not establish malicious intent.

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 code performs remote software installation rather than any visible Docsumo operation. Nothing in the chunk establishes that the Oomol installer is a necessary supporting dependency. The downloaded script's contents are not supplied, so its additional behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a network response directly into bash executes whatever script the endpoint supplies with the agent process's privileges. HTTPS protects transport but does not establish immutable installer integrity, so a compromised distribution endpoint could expose local files and credentials or modify the host; the missing-CLI prerequisite reduces exposure but does not eliminate it.

Content

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

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

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The fallback instructs the agent to execute remotely downloaded shell or PowerShell code without a separate approval step, integrity verification, or review. Although limited to a missing-CLI error, this can turn an ordinary Docsumo request into host-level code execution if the installer distribution is compromised; it overlaps with SC2 rather than representing an independent exploit.

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