Security Audit

ticktick-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

ticktick-automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Prompt Injection via Tool Arguments.

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 20, 2026 (commit 27904475). 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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Prompt Injection via Tool Arguments The skill documentation demonstrates patterns where user-provided input, such as 'your specific Ticktick task' for the `use_case` parameter in `RUBE_SEARCH_TOOLS` or dynamic arguments for `RUBE_MULTI_EXECUTE_TOOL`, could be directly passed to underlying Rube MCP tools. If these inputs are not properly sanitized or validated before being used in tool calls, an attacker could craft malicious prompts to manipulate the Rube MCP, execute unintended Ticktick operations (e.g., create/delete tasks, modify data), or exfiltrate sensitive information from the Ticktick account. This is a common vulnerability in LLM-powered agents that dynamically construct tool calls based on user input. Implement robust input validation and sanitization for all user-provided data before it is passed as arguments to `RUBE_SEARCH_TOOLS`, `RUBE_MULTI_EXECUTE_TOOL`, or any other Rube MCP tool. Ensure that the LLM's output for these fields is constrained and validated against expected schemas and safe patterns. Consider using allow-lists for `use_case` or strictly typing arguments to prevent arbitrary string injection. The agent should explicitly confirm sensitive operations with the user.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7007f405d69729af.svg)](https://skillshield.io/report/7007f405d69729af)