Back to skill

Security audit

PartnerStack Partner

Security checks for vulnerabilities and agentic risk

Overview

The PartnerStack reads fit the stated purpose, but missing-tool setup directs the agent to execute unverified remote code without a clear user approval step.

Review the setup before enabling this skill. Install a reviewed, pinned oo release separately and approve any changes to other agent skills. PartnerStack access is routed through your OOMOL-connected account. The remote installers were unavailable for inspection, so their exact local effects remain unknown.

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 chunk contains no PartnerStack data-access behavior; its sole operation is executing a remotely fetched installer. Although CLI installation can be a supporting implementation detail, nothing supplied establishes this installer's connection to the declared PartnerStack functionality. The remote script's further actions cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes an unpinned remote script directly into Bash without verifying its integrity or authenticity beyond HTTPS. If the distribution endpoint or release pipeline is compromised, attacker-controlled code would execute with the invoking user's privileges and could access local files and credentials; the PowerShell alternative has the same trust problem.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Fallback setup executes downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

A missing CLI triggers instructions to execute a remote installer without first explaining its system changes or obtaining installation-specific approval. This crosses from a read-only data request into local code execution; the missing-command condition limits when it happens but does not authorize that escalation.

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 80)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