Trust Assessment
telegram received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential for arbitrary file exfiltration via Telegram file upload, Potential for Server-Side Request Forgery (SSRF) via image URL, Skill requires and uses a sensitive Telegram Bot Token.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential for arbitrary file exfiltration via Telegram file upload The skill examples for `sendPhoto` and `sendDocument` demonstrate uploading local files using `@/path/to/file.ext`. If an AI agent implementing this skill allows user-controlled input for the file path, an attacker could specify arbitrary file paths on the agent's filesystem, leading to the exfiltration of sensitive data to a Telegram chat. This capability grants excessive read permissions to the agent. Implement strict validation and sanitization of file paths provided by user input. Restrict file access to a designated, sandboxed directory or disallow arbitrary file uploads entirely. Ensure the agent's execution environment has minimal necessary file system permissions. | LLM | SKILL.md:44 | |
| MEDIUM | Potential for Server-Side Request Forgery (SSRF) via image URL The `sendPhoto` example allows specifying a URL for the image (`"photo": "https://example.com/image.jpg"`). If an AI agent implementing this skill allows user-controlled input for this URL, an attacker could provide internal network URLs or other malicious URLs. This could lead to the agent making requests to internal services, potentially exposing sensitive information or allowing port scanning from the agent's host. Implement strict validation for URLs provided by user input. Only allow trusted domains or use a URL allowlist. Consider proxying requests through a service that can filter or sanitize URLs. | LLM | SKILL.md:37 | |
| INFO | Skill requires and uses a sensitive Telegram Bot Token The skill explicitly instructs users to store a Telegram Bot Token in `~/.config/telegram/bot_token` and demonstrates its use in API calls. While necessary for functionality, the presence of this sensitive credential in the agent's environment increases the attack surface. If other vulnerabilities (e.g., arbitrary file read, command injection) exist, this token could be compromised and used for unauthorized Telegram actions. Ensure the agent's execution environment is properly secured. Implement robust access controls for the token file. Consider using a secure secrets management system (e.g., environment variables, dedicated secrets manager) instead of plain file storage. Educate users on the risks associated with exposing bot tokens. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/75b47780c257e737)
Powered by SkillShield