Back to skill

Security audit

Superchat

Security checks for vulnerabilities and agentic risk

Overview

The Superchat operations have clear safeguards, but setup directs the agent to execute an unverified remote installer without separate user approval.

Review and approve CLI installation separately, including its automatic agent-skill installation and synchronization. Prefer a pinned, verified release and retain confirmation before messages or contact changes. OOMOL handles the connected Superchat credentials and requests. The remote installer and connector runtime remain 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
97% confidence
Finding

The supplied command executes an Oomol-hosted installer and contains no Superchat operations or evidence connecting the installation to Superchat functionality. Although dependency installation can be a supporting implementation detail, that relationship is not established here. The contents and further effects of the remote installer 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

The curl-to-bash pipeline executes mutable remote content without a pinned version or artifact verification; compromise of the distribution endpoint could result in arbitrary code execution with the invoking user's privileges. HTTPS protects transport but does not establish the integrity of a compromised publisher's script, and the adjacent PowerShell installation command has the same risk.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The fallback directs the agent to execute downloaded shell or PowerShell code without first obtaining explicit approval for local software installation or verifying the artifact. This is more than a missing warning: a missing CLI can trigger code execution with the agent's local privileges, although the conditional setup and oo-only tool declaration may limit practical reachability.

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 86)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