Back to skill

Security audit

Rocket.Chat

Security checks for vulnerabilities and agentic risk

Overview

The chat features are clearly scoped, but setup instructs the agent to run unverified downloaded software without separate approval.

Review this skill's automatic setup before use. Install the CLI separately from a verified release and review the Rocket.Chat access granted to OOMOL. Keep the required confirmations for posting, editing, and deleting messages. External installer and connector implementations were not verified; the concern is installation control, with no artifact-backed evidence of 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
95% confidence
Finding

The supplied chunk performs remote installer execution, not Rocket.Chat operations. Nothing in the chunk establishes that this installation is a supporting dependency for the declared functionality. 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
98% confidence
Finding

Piping a remotely fetched, unpinned installer directly into Bash executes its contents without prior verification; the PowerShell alternative has the same weakness. A compromised distribution endpoint could execute arbitrary code with the invoking account's permissions, including accessing local files and credentials; HTTPS does not protect against compromise of the publisher or hosting infrastructure.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installation scripts without warning about their system-level effects.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The missing-CLI fallback directs installation without first explaining local system changes or requesting installation-specific approval. This expands a Rocket.Chat task into local software execution; the conditional trigger reduces exposure but does not establish user consent for those effects.

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 83)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