Security Audit

telegram-pairing-message-customization

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

telegram-pairing-message-customization received a trust score of 83/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Instruction to execute shell command, Implied requirement for root/sudo privileges.

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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Instruction to execute shell command The skill instructs the user to execute a shell command (`openclaw gateway restart`). If an AI agent were to interpret and execute this instruction, it could lead to command injection, potentially disrupting the `openclaw` gateway service or executing arbitrary commands if the agent's execution environment is not properly sandboxed. Avoid instructing users to directly execute shell commands within skill descriptions if the skill is intended for automated interpretation. For automated agents, provide a safe API or tool call instead of raw shell commands. If manual execution is the only path, clearly state it's a manual step for a human administrator.	LLM	SKILL.md:52
MEDIUM	Implied requirement for root/sudo privileges The skill instructs the user to modify files, with a suggested starting directory of `/usr/lib/node_modules/openclaw/`. Modifying files in this system-level directory typically requires root or sudo privileges. If an AI agent were to interpret and execute these instructions, it would require excessive permissions, potentially leading to unauthorized system modifications. If the skill is intended for automated execution, ensure that any file modifications are performed through secure, sandboxed APIs with minimal necessary permissions. If it's a manual instruction, clearly state the required user privileges and warn about the risks of elevated permissions.	LLM	SKILL.md:62

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1ab29431ecd25b07.svg)](https://skillshield.io/report/1ab29431ecd25b07)