Security Audit

sundial-org/awesome-openclaw-skills:skills/apple-mail-search-2

github.com/sundial-org/awesome-openclaw-skills

AI SkillCommit 6d998e005da6

CAUTION

Scanned 27 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

sundial-org/awesome-openclaw-skills:skills/apple-mail-search-2 received a trust score of 52/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Reliance on unverified custom binary, Potential SQL Injection vulnerability in raw SQL example.

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 March 3, 2026 (commit 6d998e00). 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

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Reliance on unverified custom binary The skill requires the installation and execution of a custom binary named `mail-search`. The source code for this binary is not provided within the skill package, nor is a verifiable hash or trusted download location. This introduces a significant supply chain risk, as the binary's behavior is opaque and could potentially contain malicious code or vulnerabilities. The LLM is instructed to copy this binary to `/usr/local/bin/` and execute it, making it a critical component without transparency. Provide the source code for `mail-search` within the skill package, or a verifiable hash and a trusted download location. Implement a build process that allows for auditing of the binary.	LLM	SKILL.md:10
MEDIUM	Potential SQL Injection vulnerability in raw SQL example The 'Advanced: Raw SQL' section provides an example of directly querying the `Envelope Index` database using `sqlite3`. This example includes a `WHERE` clause with `LIKE '%your query%'`. If an LLM were to dynamically construct this command by substituting user-provided input for `your query` without proper sanitization or parameterization, it could lead to SQL injection. This could allow an attacker to manipulate the query, bypass intended filters, or potentially extract sensitive data beyond the intended scope of the query. Advise against direct insertion of untrusted input into raw SQL queries. If raw SQL is necessary, provide clear instructions on how to sanitize or parameterize inputs. For LLM usage, explicitly warn the LLM about the dangers of unsanitized input in this context and recommend using the `mail-search` tool's built-in parameters instead.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/28c2abc618d6adeb.svg)](https://skillshield.io/report/28c2abc618d6adeb)