Trust Assessment
tg-image-sender received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential local file exfiltration via 'media' parameter.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential local file exfiltration via 'media' parameter The skill's documentation states that the 'media' parameter for the 'message' tool can accept an 'actual URL/media path'. If 'media path' refers to local filesystem paths (e.g., `/etc/passwd`, `/home/user/secrets.txt`), and the underlying 'message' tool is capable of reading and sending arbitrary local files, this could lead to data exfiltration. An attacker could craft a prompt to instruct the LLM to provide sensitive local file paths, leading to their content being sent to the Telegram chat. This also implies the 'message' tool might possess excessive permissions to read the local filesystem. Clarify the acceptable values for the 'media' parameter. If local file paths are intended, restrict access to a sandboxed directory and implement strict validation to prevent arbitrary file reads. If only URLs are intended, remove 'media path' from the documentation and explicitly state that only URLs are supported. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/410689bb0d4edc60)
Powered by SkillShield