Back to skill

Security audit

Telegram Bot

Security checks for vulnerabilities and agentic risk

Overview

This Telegram integration needs review because its setup executes unverified remote code and one user-facing action bypasses its confirmation rules.

Review and install a verified CLI release separately, including its automatic skill-installation behavior. Connect only the bot and permissions needed, and require approval for callback notifications as well as messaging, moderation, and deletion. Remote installer and hosted connector implementations were not verified; the inspected artifact does not establish 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 (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk is a remote installer command, not a Telegram Bot integration. Although installation can be a supporting implementation detail, the provided content establishes no connection between this installer and the declared Telegram functionality. The remote script's contents and subsequent effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

The only supplied command invokes authentication and does not identify Telegram or perform any declared bot-data operation. Authentication could support a broader integration, but no such connection is shown here; as supplied, the code's sole behavior materially differs from the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a mutable remote script directly into bash executes its contents with the agent process's local privileges without a pinned version or independent integrity verification. Compromise of the distribution service could therefore lead to local code execution and access to files or credentials; HTTPS and the legitimate dependency relationship do not eliminate that supply-chain risk.

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

The safety guidance classifies answer_callback_query as a read despite its user-visible effects.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The untagged answer_callback_query action falls under the instruction that untagged actions are reads and safe to run directly, although it can display notifications or alerts to Telegram users. This creates a concrete exception to the skill's confirmation boundary, allowing externally visible effects without the approval required for other writes.

Content

No source excerpt is available for this finding.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The missing-CLI fallback directs the agent to execute a downloaded installer without explicitly obtaining approval for local software installation or explaining its system changes. Although setup is relevant and conditional, permission to perform Telegram operations does not necessarily authorize running vendor-controlled code on the local machine.

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 125)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