Back to skill

Security audit

Discourse

Security checks for vulnerabilities and agentic risk

Overview

Review the setup before installing: it directs automatic execution of remote code and omits the CLI’s documented changes to other agents’ skills.

Approve CLI installation separately and verify a fixed release before executing it. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization; consider setting it before running the CLI. Use only the intended Discourse account and confirm public post contents. The remote installers’ complete effects remain unverified.

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
96% confidence
Finding

The supplied code installs a third-party CLI rather than performing Discourse operations. Nothing in the chunk establishes this installation as a supporting dependency for Discourse. The remote script's contents are not supplied, so its additional effects cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

Piping a remotely fetched script directly into Bash executes mutable external code without prior review or independent integrity verification; the PowerShell alternative has the same weakness. Compromise of the installer delivery path could execute attacker-controlled code with the agent's local permissions, although the missing-CLI condition and any enforced tool restrictions limit when this path is reachable.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The missing-CLI fallback instructs the agent to install software without obtaining approval for local code execution and system changes, which exceeds an ordinary Discourse data request. The explicit confirmation requirements cover Discourse writes but not installation; strict enforcement of the declared Bash(oo *) tool restriction would reduce exposure by blocking the shown installation commands.

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 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