Back to skill

Security audit

GatherUp

Security checks for vulnerabilities and agentic risk

Overview

The GatherUp reader needs review because its setup runs unverified installation scripts and leaves broader changes to agent skills undisclosed.

Review and approve CLI installation separately before allowing setup to run. Use a verified release and disable startup skill synchronization with the publisher-documented OO_SKILLS_SYNC_DISABLED=1 control if you do not want other agent skills changed. Confirm that routing GatherUp customer data through OOMOL is acceptable. The complete bundled skill was inspected; the remote installer and hosted connector implementation remain outside the verified artifact.

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 code runs a remote installer rather than searching or reading GatherUp data. No connection between this installer and the declared GatherUp functionality is established, so it cannot be treated as a demonstrated supporting implementation detail. The installer's contents and further effects are not shown.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

The supplied code performs only a login operation and contains no GatherUp-specific access, search, or reading behavior. Authentication could support the declared purpose, but this chunk provides no connection to GatherUp and implements authentication as its sole behavior.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command immediately executes mutable remote content without version pinning or independent integrity verification. If the distribution endpoint or release pipeline is compromised, the script could execute arbitrary commands with the invoking user's privileges; HTTPS and a legitimate dependency purpose do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local code execution and system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

When the CLI is missing, the skill instructs installation through a remote shell or PowerShell script without requiring informed approval for local code execution and system changes. Although this is a plausible dependency setup step, it expands a read-only data request into software installation; the declared oo-only tool restriction may limit execution but does not make the instruction safe.

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 79)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