Security Audit
telegram-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
telegram-automation received a trust score of 89/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Skill enables retrieval and potential exfiltration of sensitive Telegram data, Skill enables generation and potential misuse of chat invite links.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Skill enables retrieval and potential exfiltration of sensitive Telegram data The skill provides access to tools such as `TELEGRAM_GET_UPDATES` and `TELEGRAM_GET_CHAT_HISTORY` which can retrieve private messages and chat information. It also includes tools like `TELEGRAM_SEND_MESSAGE`, `TELEGRAM_SEND_PHOTO`, and `TELEGRAM_SEND_DOCUMENT` that can be used to transmit this retrieved data to arbitrary chats or users. A compromised LLM agent, if subjected to prompt injection, could combine these capabilities to exfiltrate sensitive user data from Telegram. Implement strict access controls and user consent mechanisms for tools that retrieve or transmit sensitive data. Ensure the LLM agent is robustly protected against prompt injection to prevent misuse of these capabilities. Carefully consider the scope of data access granted to the bot. | LLM | SKILL.md:140 | |
| MEDIUM | Skill enables generation and potential misuse of chat invite links The skill includes the `TELEGRAM_EXPORT_CHAT_INVITE_LINK` tool, which can generate invite links for Telegram chats. The documentation explicitly states that 'Bot must be an administrator to export invite links.' If the bot is granted administrative privileges, a compromised LLM agent could be prompted to generate and share invite links for private groups or channels, potentially leading to unauthorized access or disclosure of group membership. Carefully review the minimum required permissions for the Telegram bot. Avoid granting administrative privileges unless absolutely necessary. Implement strict controls and user confirmation for actions involving the generation or sharing of invite links to prevent unauthorized access. | LLM | SKILL.md:109 |
Scan History
Embed Code
[](https://skillshield.io/report/899534a6420669ec)
Powered by SkillShield